├── README.md
├── dataset
    ├── EC
    │   ├── dev.json
    │   ├── test.json
    │   └── train.json
    └── MSRA
    │   ├── dev.json
    │   ├── test.json
    │   └── train.json
├── main.py
├── misc.py
├── model.py
├── requirements.txt
├── resource
    ├── bert-base-chinese
    │   └── vocab.txt
    └── conlleval.pl
├── save
    └── readme.md
├── train_EC.sh
├── train_NEWS.sh
└── utils.py


/README.md:
--------------------------------------------------------------------------------
 1 | # SCL-RAI
 2 | Hi, this is the code of our paper "SCL-RAI: Span-based Contrastive Learning with Retrieval Augmented Inference for Unlabeled Entity Problem in NER" accepted by COLING 2022. Our paper is available [here](https://arxiv.org/pdf/2209.01646.pdf).
 3 | 
 4 | News:
 5 | 
 6 | Accepted by COLING 2022. 2022.08.16
 7 | 
 8 | Code released at Github. 2022.08.16
 9 | 
10 | ## Preparation
11 | 1. Download pretrained LM: bert-base-chinese [model.pt](https://drive.google.com/drive/folders/1gZHmImlXDX6-uJaMvcYJf24ZwMCeq1P-?usp=sharing) and put it into resource/bert-base-chinese
12 | 2. Use requirements.txt to get the right environments.
13 | 
14 | 
15 | ## Reproduce results
16 | For EC: 
17 | >sh train_EC.sh
18 | 
19 | For NEWS: 
20 | >sh train_NEWS.sh
21 | 
22 | 
23 | We got our results in single A40.
24 | 


--------------------------------------------------------------------------------
/dataset/EC/dev.json:
--------------------------------------------------------------------------------
   1 | [
   2 |  {
   3 |   "sentence": "['想', '买', '件', '牧', '王', '羊', '绒', '大', '衣', '修', '身', '款', '，', '朋', '友', '有', '一', '件', '很', '漂', '亮', '。', '上', '身', '显', '气', '质', '，', '帅', '气', '。', '就', '是', '找', '不', '到', '。', '请', '问', '我', '怎', '样', '才', '能', '买', '到', '。']",
   4 |   "labeled entities": "[(3, 4, 'pp'), (7, 8, 'cp')]"
   5 |  },
   6 |  {
   7 |   "sentence": "['我', '要', '买', '洋', '酒']",
   8 |   "labeled entities": "[(3, 4, 'cp')]"
   9 |  },
  10 |  {
  11 |   "sentence": "['买', '化', '妆', '品', '什', '么', '行', '就', '是', '买', '衣', '服', '，', '不', '行']",
  12 |   "labeled entities": "[(1, 3, 'cp'), (10, 11, 'cp')]"
  13 |  },
  14 |  {
  15 |   "sentence": "['我', '想', '买', '抹', '茶', '点', '心']",
  16 |   "labeled entities": "[(5, 6, 'cp')]"
  17 |  },
  18 |  {
  19 |   "sentence": "['我', '想', '找', '我', '之', '前', '买', '裤', '子', '的', '商', '户', '，', '可', '是', '我', '找', '不', '到', '哪', '一', '家']",
  20 |   "labeled entities": "[(7, 8, 'cp')]"
  21 |  },
  22 |  {
  23 |   "sentence": "['不', '倒', '绒', '连', '体', '衣']",
  24 |   "labeled entities": "[(3, 5, 'cp')]"
  25 |  },
  26 |  {
  27 |   "sentence": "['想', '买', '件', '短', '外', '套', '，', '女']",
  28 |   "labeled entities": "[(4, 5, 'cp')]"
  29 |  },
  30 |  {
  31 |   "sentence": "['休', '闲', '甜', '美']",
  32 |   "labeled entities": "[]"
  33 |  },
  34 |  {
  35 |   "sentence": "['胖', '人', '显', '瘦', '的', '衣', '服']",
  36 |   "labeled entities": "[(5, 6, 'cp')]"
  37 |  },
  38 |  {
  39 |   "sentence": "['凉', '鞋', '小', '学', '生', '女']",
  40 |   "labeled entities": "[(0, 1, 'cp')]"
  41 |  },
  42 |  {
  43 |   "sentence": "['首', '页', '里', '面', '都', '是', '吃', '的', '，', '在', '哪', '看', '衣', '服', '呢']",
  44 |   "labeled entities": "[(12, 13, 'cp')]"
  45 |  },
  46 |  {
  47 |   "sentence": "['崖', '柏']",
  48 |   "labeled entities": "[(0, 1, 'cp')]"
  49 |  },
  50 |  {
  51 |   "sentence": "['我', '要', '活', '的']",
  52 |   "labeled entities": "[]"
  53 |  },
  54 |  {
  55 |   "sentence": "['那', '种', '比', '较', '好']",
  56 |   "labeled entities": "[]"
  57 |  },
  58 |  {
  59 |   "sentence": "['我', '要', '买', '触', '屏', '生', '命', '树', '手', '表']",
  60 |   "labeled entities": "[(8, 9, 'cp')]"
  61 |  },
  62 |  {
  63 |   "sentence": "['查', '看', '物', '流']",
  64 |   "labeled entities": "[]"
  65 |  },
  66 |  {
  67 |   "sentence": "['夏', '天', '短', '袖']",
  68 |   "labeled entities": "[(2, 3, 'cp')]"
  69 |  },
  70 |  {
  71 |   "sentence": "['像', '丸', '子', '会', '飞', '的', '汽', '车']",
  72 |   "labeled entities": "[(6, 7, 'cp')]"
  73 |  },
  74 |  {
  75 |   "sentence": "['星', '星', '网', '纱', '上', '配', '小', '皇', '冠']",
  76 |   "labeled entities": "[]"
  77 |  },
  78 |  {
  79 |   "sentence": "['骨', '架', '大']",
  80 |   "labeled entities": "[]"
  81 |  },
  82 |  {
  83 |   "sentence": "['买', '裤', '子', '不', '知', '道', '自', '己', '是', '多', '大', '的', '腰', '围']",
  84 |   "labeled entities": "[(1, 2, 'cp')]"
  85 |  },
  86 |  {
  87 |   "sentence": "['桃', '红']",
  88 |   "labeled entities": "[]"
  89 |  },
  90 |  {
  91 |   "sentence": "['外', '套', '中', '款']",
  92 |   "labeled entities": "[(0, 1, 'cp')]"
  93 |  },
  94 |  {
  95 |   "sentence": "['手', '工', '制', '作', '相', '册']",
  96 |   "labeled entities": "[(4, 5, 'cp')]"
  97 |  },
  98 |  {
  99 |   "sentence": "['厚', '实']",
 100 |   "labeled entities": "[]"
 101 |  },
 102 |  {
 103 |   "sentence": "['价', '格', '最', 'm', 's', 'a', 't', 'a', '硬', '盘', '1', '2', '8', 'G']",
 104 |   "labeled entities": "[(8, 9, 'cp'), (10, 13, 'gg')]"
 105 |  },
 106 |  {
 107 |   "sentence": "['有', '没', '有', '儿', '童', '双', '人', '手', '推', '车']",
 108 |   "labeled entities": "[(7, 9, 'cp')]"
 109 |  },
 110 |  {
 111 |   "sentence": "['运', '动', '鞋', '子']",
 112 |   "labeled entities": "[(2, 3, 'cp')]"
 113 |  },
 114 |  {
 115 |   "sentence": "['水', '壶', '3', '，', '4', '块', '钱', '的']",
 116 |   "labeled entities": "[(0, 1, 'cp')]"
 117 |  },
 118 |  {
 119 |   "sentence": "['电', '脑', '风', '扇']",
 120 |   "labeled entities": "[(0, 3, 'cp')]"
 121 |  },
 122 |  {
 123 |   "sentence": "['香', '水', '女']",
 124 |   "labeled entities": "[(0, 1, 'cp')]"
 125 |  },
 126 |  {
 127 |   "sentence": "['我', '要', '1', '段', '奶', '粉']",
 128 |   "labeled entities": "[(4, 5, 'cp')]"
 129 |  },
 130 |  {
 131 |   "sentence": "['魅', '族', 'p', 'r', 'o', '6', 'p', 'l', 'u', 's']",
 132 |   "labeled entities": "[(0, 1, 'pp'), (2, 9, 'xh')]"
 133 |  },
 134 |  {
 135 |   "sentence": "['数', '字', '电', '视', '天', '线']",
 136 |   "labeled entities": "[(4, 5, 'cp')]"
 137 |  },
 138 |  {
 139 |   "sentence": "['国', '产', '的']",
 140 |   "labeled entities": "[]"
 141 |  },
 142 |  {
 143 |   "sentence": "['牛', '仔', '衣', '假', '两', '件', '套']",
 144 |   "labeled entities": "[(0, 2, 'cp'), (4, 6, 'cp')]"
 145 |  },
 146 |  {
 147 |   "sentence": "['女', '式', '情', '趣', '用', '品']",
 148 |   "labeled entities": "[(2, 5, 'cp')]"
 149 |  },
 150 |  {
 151 |   "sentence": "['以', '后', '不', '要', '给', '我', '推', '荐', '韩', '货', '，', '任', '何', '韩', '国', '都', '不', '要']",
 152 |   "labeled entities": "[]"
 153 |  },
 154 |  {
 155 |   "sentence": "['五', '十', '岁', '爸', '爸', '装']",
 156 |   "labeled entities": "[(3, 5, 'cp')]"
 157 |  },
 158 |  {
 159 |   "sentence": "['茶', '具', '套', '装']",
 160 |   "labeled entities": "[(0, 3, 'cp')]"
 161 |  },
 162 |  {
 163 |   "sentence": "['想', '买', '祛', '斑', '效', '果', '好', '点', '的', '祛', '斑', '霜']",
 164 |   "labeled entities": "[(9, 11, 'cp')]"
 165 |  },
 166 |  {
 167 |   "sentence": "['鲁', '花', '花', '生', '油']",
 168 |   "labeled entities": "[(0, 1, 'pp'), (2, 4, 'cp')]"
 169 |  },
 170 |  {
 171 |   "sentence": "['小', '糖', '果']",
 172 |   "labeled entities": "[(1, 2, 'cp')]"
 173 |  },
 174 |  {
 175 |   "sentence": "['我', '想', '找', '电', '脑', '板', '，', '找', '不', '到']",
 176 |   "labeled entities": "[(3, 5, 'cp')]"
 177 |  },
 178 |  {
 179 |   "sentence": "['我', '要', '买', '原', '创', '服', '装']",
 180 |   "labeled entities": "[(5, 6, 'cp')]"
 181 |  },
 182 |  {
 183 |   "sentence": "['祛', '红', '血', '丝']",
 184 |   "labeled entities": "[]"
 185 |  },
 186 |  {
 187 |   "sentence": "['防', '热', '垫']",
 188 |   "labeled entities": "[(0, 2, 'cp')]"
 189 |  },
 190 |  {
 191 |   "sentence": "['九', '个', '月', '宝', '宝', '奶', '粉']",
 192 |   "labeled entities": "[(3, 6, 'cp')]"
 193 |  },
 194 |  {
 195 |   "sentence": "['风', '衣', '外', '套']",
 196 |   "labeled entities": "[(0, 1, 'cp'), (2, 3, 'cp')]"
 197 |  },
 198 |  {
 199 |   "sentence": "['双', '人', '床']",
 200 |   "labeled entities": "[(0, 2, 'cp')]"
 201 |  },
 202 |  {
 203 |   "sentence": "['薄', '膜', '粘', '在', '防', '盗', '门', '上', '应', '该', '用', '什', '么', '产', '品', '清', '洗']",
 204 |   "labeled entities": "[]"
 205 |  },
 206 |  {
 207 |   "sentence": "['面', '膜', '美', '白']",
 208 |   "labeled entities": "[(0, 1, 'cp')]"
 209 |  },
 210 |  {
 211 |   "sentence": "['大', '功', '率']",
 212 |   "labeled entities": "[]"
 213 |  },
 214 |  {
 215 |   "sentence": "['我', '想', '找', '一', '款', '包']",
 216 |   "labeled entities": "[(5, 5, 'cp')]"
 217 |  },
 218 |  {
 219 |   "sentence": "['买', '苹', '果', '手', '机', '骗', '钱', '怎', '么', '办']",
 220 |   "labeled entities": "[(1, 2, 'pp'), (3, 4, 'cp')]"
 221 |  },
 222 |  {
 223 |   "sentence": "['婴', '舒', '宝', '超', '薄', '拉', '拉', '裤']",
 224 |   "labeled entities": "[(0, 2, 'pp'), (5, 7, 'cp')]"
 225 |  },
 226 |  {
 227 |   "sentence": "['泡', '爪', ' ', '罐', '装']",
 228 |   "labeled entities": "[(0, 1, 'cp')]"
 229 |  },
 230 |  {
 231 |   "sentence": "['男', '式', '休', '闲', '上', '衣']",
 232 |   "labeled entities": "[(4, 5, 'cp')]"
 233 |  },
 234 |  {
 235 |   "sentence": "['童', '装', '时', '尚', '点', '的']",
 236 |   "labeled entities": "[(0, 1, 'cp')]"
 237 |  },
 238 |  {
 239 |   "sentence": "['那', '个', '魅', '族', 'm', 'x', '5', '有', '吗', '？']",
 240 |   "labeled entities": "[(2, 3, 'pp'), (4, 6, 'xh')]"
 241 |  },
 242 |  {
 243 |   "sentence": "['甜', '水', '果']",
 244 |   "labeled entities": "[(1, 2, 'cp')]"
 245 |  },
 246 |  {
 247 |   "sentence": "['我', '想', '找', '二', '手', '苹', '果', '6', 's', 'p', '手', '机']",
 248 |   "labeled entities": "[(5, 6, 'pp'), (7, 9, 'xh'), (10, 11, 'cp')]"
 249 |  },
 250 |  {
 251 |   "sentence": "['我', '要', '买', '铅', '笔', '盒']",
 252 |   "labeled entities": "[(3, 5, 'cp')]"
 253 |  },
 254 |  {
 255 |   "sentence": "['高', '腰', '白', '色', '蕾', '丝', '裙']",
 256 |   "labeled entities": "[(4, 6, 'cp')]"
 257 |  },
 258 |  {
 259 |   "sentence": "['裤', '子', '男', '亮', '色', '，', '宽', '松', '裤', '子', '男', '长', '裤']",
 260 |   "labeled entities": "[(0, 1, 'cp'), (8, 9, 'cp'), (11, 12, 'cp')]"
 261 |  },
 262 |  {
 263 |   "sentence": "['尖', '头', '小', '白', '鞋']",
 264 |   "labeled entities": "[(4, 4, 'cp')]"
 265 |  },
 266 |  {
 267 |   "sentence": "['电', '蚊', '拍']",
 268 |   "labeled entities": "[(0, 2, 'cp')]"
 269 |  },
 270 |  {
 271 |   "sentence": "['收', '缩']",
 272 |   "labeled entities": "[]"
 273 |  },
 274 |  {
 275 |   "sentence": "['黄', '花', '梨']",
 276 |   "labeled entities": "[]"
 277 |  },
 278 |  {
 279 |   "sentence": "['你', '推', '荐', '的', '不', '是', '我', '需', '要', '的']",
 280 |   "labeled entities": "[]"
 281 |  },
 282 |  {
 283 |   "sentence": "['我', '要', '买', '咬', '咬', '乐']",
 284 |   "labeled entities": "[(3, 5, 'cp')]"
 285 |  },
 286 |  {
 287 |   "sentence": "['适', '合', '4', '0', '岁', '以', '下', '的', '人', '穿', '的', '风', '衣']",
 288 |   "labeled entities": "[(11, 12, 'cp')]"
 289 |  },
 290 |  {
 291 |   "sentence": "['漂', '亮', '有', '个', '性', '的', '台', '灯']",
 292 |   "labeled entities": "[(6, 7, 'cp')]"
 293 |  },
 294 |  {
 295 |   "sentence": "['买', 'Q', '币', '为', '什', '么', '不', '加', '购', '物', '总', '额', '？']",
 296 |   "labeled entities": "[(1, 2, 'cp')]"
 297 |  },
 298 |  {
 299 |   "sentence": "['花', '格', '衬', '衫']",
 300 |   "labeled entities": "[(2, 3, 'cp')]"
 301 |  },
 302 |  {
 303 |   "sentence": "['原', '味']",
 304 |   "labeled entities": "[]"
 305 |  },
 306 |  {
 307 |   "sentence": "['购', '买', '洗', '发', '水']",
 308 |   "labeled entities": "[(2, 4, 'cp')]"
 309 |  },
 310 |  {
 311 |   "sentence": "['男', '小', '白', '鞋']",
 312 |   "labeled entities": "[(3, 3, 'cp')]"
 313 |  },
 314 |  {
 315 |   "sentence": "['一', '百', '五', '十', '元', '的', '手', '机', '有', '哪', '些']",
 316 |   "labeled entities": "[(6, 7, 'cp')]"
 317 |  },
 318 |  {
 319 |   "sentence": "['中', '年', '的']",
 320 |   "labeled entities": "[]"
 321 |  },
 322 |  {
 323 |   "sentence": "['女', '运', '动', '服', '大', '码']",
 324 |   "labeled entities": "[(1, 3, 'cp')]"
 325 |  },
 326 |  {
 327 |   "sentence": "['华', '尔', '贝', '矿', '灯', '，', '充', '电', '后', '久', '用', '，', '最', '好', '的']",
 328 |   "labeled entities": "[(0, 2, 'pp'), (3, 4, 'cp')]"
 329 |  },
 330 |  {
 331 |   "sentence": "['蓝', '牙', '耳', '机', '上', '的', '副', '耳', '机', '上', '没', '有', '耳', '帽', '。']",
 332 |   "labeled entities": "[(2, 3, 'cp'), (7, 8, 'cp'), (12, 13, 'cp')]"
 333 |  },
 334 |  {
 335 |   "sentence": "['绿', '色', '卫', '衣', '配', '什', '么', '外', '套', '好', '看', '啊']",
 336 |   "labeled entities": "[(2, 3, 'cp'), (7, 8, 'cp')]"
 337 |  },
 338 |  {
 339 |   "sentence": "['高', '跟', '鞋']",
 340 |   "labeled entities": "[(0, 2, 'cp')]"
 341 |  },
 342 |  {
 343 |   "sentence": "['有', '妹', '子', '吗']",
 344 |   "labeled entities": "[]"
 345 |  },
 346 |  {
 347 |   "sentence": "['我', '不', '要', '看', '什', '么', '宝', '宝', '的', '书', '还', '没', '结', '婚', '呢']",
 348 |   "labeled entities": "[(9, 9, 'cp')]"
 349 |  },
 350 |  {
 351 |   "sentence": "['要', '2', '0', '岁', '人', '穿', '的', '裙', '子']",
 352 |   "labeled entities": "[(7, 8, 'cp')]"
 353 |  },
 354 |  {
 355 |   "sentence": "['男', '女', '都', '能', '穿', '的', '外', '套', '，', '好', '看', '的']",
 356 |   "labeled entities": "[(6, 7, 'cp')]"
 357 |  },
 358 |  {
 359 |   "sentence": "['华', '为', '荣', '耀', 'm', 'a', 'g', 'i', 'c', '好', '看', '的', '套']",
 360 |   "labeled entities": "[(0, 1, 'pp'), (2, 3, 'pp'), (4, 8, 'xh'), (12, 12, 'cp')]"
 361 |  },
 362 |  {
 363 |   "sentence": "['便', '宜', '好', '用', '的']",
 364 |   "labeled entities": "[]"
 365 |  },
 366 |  {
 367 |   "sentence": "['小', '米', '4', 'S']",
 368 |   "labeled entities": "[(0, 1, 'pp'), (2, 3, 'xh')]"
 369 |  },
 370 |  {
 371 |   "sentence": "['男', '士', '跑', '步', '鞋', '，', '透', '气', '性', '好', '的']",
 372 |   "labeled entities": "[(2, 4, 'cp')]"
 373 |  },
 374 |  {
 375 |   "sentence": "['拼', '色', '襯', '衫']",
 376 |   "labeled entities": "[(2, 3, 'cp')]"
 377 |  },
 378 |  {
 379 |   "sentence": "['还', '是', '夜', '光', '鞋', '呀', '三', '十', '八', '码', '的']",
 380 |   "labeled entities": "[(2, 4, 'cp'), (6, 9, 'gg')]"
 381 |  },
 382 |  {
 383 |   "sentence": "['2', '0', '-', '3', '0']",
 384 |   "labeled entities": "[]"
 385 |  },
 386 |  {
 387 |   "sentence": "['一', '件', '宽', '松', '时', '尚', '带', '帽', '子', '的', '女', '士', '卫', '衣']",
 388 |   "labeled entities": "[(12, 13, 'cp')]"
 389 |  },
 390 |  {
 391 |   "sentence": "['免', '洗', '睡', '眠', '面', '膜']",
 392 |   "labeled entities": "[(4, 5, 'cp')]"
 393 |  },
 394 |  {
 395 |   "sentence": "['白', '色', '尖', '头', '细', '跟', '高', '跟', '鞋']",
 396 |   "labeled entities": "[(6, 8, 'cp')]"
 397 |  },
 398 |  {
 399 |   "sentence": "['有', '没', '有', '女', '吃', '的', '伟', '哥']",
 400 |   "labeled entities": "[(6, 7, 'cp')]"
 401 |  },
 402 |  {
 403 |   "sentence": "['变', '色', '口', '红']",
 404 |   "labeled entities": "[(2, 3, 'cp')]"
 405 |  },
 406 |  {
 407 |   "sentence": "['哈', '喽', '运', '动', '裤']",
 408 |   "labeled entities": "[(2, 4, 'cp')]"
 409 |  },
 410 |  {
 411 |   "sentence": "['有', '没', '有', '好', '看', '的', '斜', '挎', '包']",
 412 |   "labeled entities": "[(6, 8, 'cp')]"
 413 |  },
 414 |  {
 415 |   "sentence": "['我', '想', '要', '2', '0', '岁', '的', '浅', '口', '单', '鞋']",
 416 |   "labeled entities": "[(7, 10, 'cp')]"
 417 |  },
 418 |  {
 419 |   "sentence": "['现', '在', '哪', '款', '手', '机', '好', '用']",
 420 |   "labeled entities": "[(4, 5, 'cp')]"
 421 |  },
 422 |  {
 423 |   "sentence": "['去', '鸡', '皮', '皂']",
 424 |   "labeled entities": "[(3, 3, 'cp')]"
 425 |  },
 426 |  {
 427 |   "sentence": "['我', '要', '买', 'h', 'e', 'l', 'l', 'o', ' ', 'k', 'i', 't', 'y', '美', '妆', '蛋']",
 428 |   "labeled entities": "[(3, 12, 'pp'), (13, 15, 'cp')]"
 429 |  },
 430 |  {
 431 |   "sentence": "['我', '想', '买', '气', '垫']",
 432 |   "labeled entities": "[(3, 4, 'cp')]"
 433 |  },
 434 |  {
 435 |   "sentence": "['亲', '亲', '，', '您', '是', '想', '要', '咨', '询', '极', '速', '退', '款', '的', '什', '么', '问', '题', '呢', '？', '小', '蜜', '猜', '您', '想', '知', '道', '的', '一', '定', '在', '下', '面', '，', '直', '接', '点', '击', '查', '看', '吧', '~', ' ', '为', '什', '么', '我', '之', '前', '能', '够', '享', '受', '“', '极', '速', '退', '款', '”', '，', '现', '在', '却', '不', '可', '以', '？']",
 436 |   "labeled entities": "[]"
 437 |  },
 438 |  {
 439 |   "sentence": "['1', '8', '到', '2', '4', '岁']",
 440 |   "labeled entities": "[]"
 441 |  },
 442 |  {
 443 |   "sentence": "['1', '0', '0', '以', '下']",
 444 |   "labeled entities": "[]"
 445 |  },
 446 |  {
 447 |   "sentence": "['喝', '奶', '奶']",
 448 |   "labeled entities": "[]"
 449 |  },
 450 |  {
 451 |   "sentence": "['牛', '津', '背', '包']",
 452 |   "labeled entities": "[(2, 3, 'cp')]"
 453 |  },
 454 |  {
 455 |   "sentence": "['袜', '子', '。']",
 456 |   "labeled entities": "[(0, 1, 'cp')]"
 457 |  },
 458 |  {
 459 |   "sentence": "['我', '要', '买', '男', '童', '春', '季', '运', '动', '鞋']",
 460 |   "labeled entities": "[(7, 9, 'cp')]"
 461 |  },
 462 |  {
 463 |   "sentence": "['我', '要', '买', '毛', '孔', '收', '缩', '液']",
 464 |   "labeled entities": "[(3, 7, 'cp')]"
 465 |  },
 466 |  {
 467 |   "sentence": "['待', '产', '包', '什', '么', '牌', '子', '的', '好']",
 468 |   "labeled entities": "[(0, 2, 'cp')]"
 469 |  },
 470 |  {
 471 |   "sentence": "['有', '没', '有', '便', '宜', '的', '工', '作', '服']",
 472 |   "labeled entities": "[(6, 8, 'cp')]"
 473 |  },
 474 |  {
 475 |   "sentence": "['仿', '藤']",
 476 |   "labeled entities": "[]"
 477 |  },
 478 |  {
 479 |   "sentence": "['芋', '头', '片']",
 480 |   "labeled entities": "[(0, 2, 'cp')]"
 481 |  },
 482 |  {
 483 |   "sentence": "['2', '万', '毫', '安', '移', '动', '电', '源']",
 484 |   "labeled entities": "[(0, 3, 'gg'), (4, 7, 'cp')]"
 485 |  },
 486 |  {
 487 |   "sentence": "['适', '合', '胖', '子', '穿', '的', '裙', '子']",
 488 |   "labeled entities": "[(6, 7, 'cp')]"
 489 |  },
 490 |  {
 491 |   "sentence": "['实', '木', '儿', '童', '床']",
 492 |   "labeled entities": "[(2, 4, 'cp')]"
 493 |  },
 494 |  {
 495 |   "sentence": "['复', '古', '磨', '砂', '大', '框', '防', '辐', '射', '眼', '镜']",
 496 |   "labeled entities": "[(9, 10, 'cp')]"
 497 |  },
 498 |  {
 499 |   "sentence": "['便', '宜', '的', '棉', '花', '糖', '机']",
 500 |   "labeled entities": "[(3, 6, 'cp')]"
 501 |  },
 502 |  {
 503 |   "sentence": "['我', '要', '找', '黄', '金', '棒']",
 504 |   "labeled entities": "[(3, 5, 'cp')]"
 505 |  },
 506 |  {
 507 |   "sentence": "['找', '好', '货', '，', '伪', '装', '网']",
 508 |   "labeled entities": "[]"
 509 |  },
 510 |  {
 511 |   "sentence": "['简', '装', '衣', '柜']",
 512 |   "labeled entities": "[(2, 3, 'cp')]"
 513 |  },
 514 |  {
 515 |   "sentence": "['哺', '乳', '外', '出', '衣']",
 516 |   "labeled entities": "[(0, 4, 'cp')]"
 517 |  },
 518 |  {
 519 |   "sentence": "['我', '要', '买', '好', '一', '点', '的', '被', '子']",
 520 |   "labeled entities": "[(7, 8, 'cp')]"
 521 |  },
 522 |  {
 523 |   "sentence": "['求', '婚', '蜡', '烛']",
 524 |   "labeled entities": "[(2, 3, 'cp')]"
 525 |  },
 526 |  {
 527 |   "sentence": "['我', '想', '要', '一', '条', '背', '带', '裤', '亲']",
 528 |   "labeled entities": "[(5, 7, 'cp')]"
 529 |  },
 530 |  {
 531 |   "sentence": "['办', '公', '室', '养', '水', '培', '植', '物', '好', '还', '是', '土', '培', '植', '物', '好', '?']",
 532 |   "labeled entities": "[(4, 7, 'cp'), (11, 14, 'cp')]"
 533 |  },
 534 |  {
 535 |   "sentence": "['孕', '妇', '连', '衣', '裙']",
 536 |   "labeled entities": "[(2, 4, 'cp')]"
 537 |  },
 538 |  {
 539 |   "sentence": "['4', '5', '-', '5', '0', 'c', 'm', '毛', '绒', '玩', '具']",
 540 |   "labeled entities": "[(0, 6, 'gg'), (7, 10, 'cp')]"
 541 |  },
 542 |  {
 543 |   "sentence": "['我', '想', '要', '改', '一', '下', '我', '的', '收', '货', '地', '址', '，', '怎', '么', '改', '小', '蜜', '？']",
 544 |   "labeled entities": "[]"
 545 |  },
 546 |  {
 547 |   "sentence": "['儿', '童', '帐', '篷']",
 548 |   "labeled entities": "[(0, 3, 'cp')]"
 549 |  },
 550 |  {
 551 |   "sentence": "['我', '想', '买', '铅', '笔', '裤']",
 552 |   "labeled entities": "[(3, 5, 'cp')]"
 553 |  },
 554 |  {
 555 |   "sentence": "['我', '要', '男', '士', '短', '袖']",
 556 |   "labeled entities": "[]"
 557 |  },
 558 |  {
 559 |   "sentence": "['我', '要', '买', '正', '宗', '的', '火', '鸡', '面']",
 560 |   "labeled entities": "[(6, 8, 'cp')]"
 561 |  },
 562 |  {
 563 |   "sentence": "['应', '该', '不', '是', '敏', '感', '肌', '肤']",
 564 |   "labeled entities": "[]"
 565 |  },
 566 |  {
 567 |   "sentence": "['我', '要', '买', '鬼', '火', '一', '代', '天', '使', '眼']",
 568 |   "labeled entities": "[(3, 6, 'xh'), (7, 9, 'cp')]"
 569 |  },
 570 |  {
 571 |   "sentence": "['我', '要', '买', '隔', '离', ' ', '气', '垫']",
 572 |   "labeled entities": "[(6, 7, 'cp')]"
 573 |  },
 574 |  {
 575 |   "sentence": "['有', '没', '有', '假', '人', '试', '衣', '服']",
 576 |   "labeled entities": "[(6, 7, 'cp')]"
 577 |  },
 578 |  {
 579 |   "sentence": "['他', '就', '说', '，', '那', '你', '只', '能', '呃', '，', '嗯', '，', '再', '问', '呃', '，', '既', '然', '停', '产', '了', '，', '我', '怎', '么', '会', '有', '呢', '，', '就', '是', '一', '直', '用', '反', '问', '的', '语', '气', '，', '去', '跟', '我', '交', '流', '，', '然', '后', '嗯', '之', '前', '有', '一', '句', '话', '说', '到', '兔', '子', '质', '量', '好', '，', '托', '跟', '奥', '迪', '的', '也']",
 580 |   "labeled entities": "[(65, 66, 'pp')]"
 581 |  },
 582 |  {
 583 |   "sentence": "['兰', '瑟', 'B', 'B', '霜']",
 584 |   "labeled entities": "[(0, 1, 'pp'), (2, 4, 'cp')]"
 585 |  },
 586 |  {
 587 |   "sentence": "['不', '是', '，', '有', '什', '么', '推', '荐', '的']",
 588 |   "labeled entities": "[]"
 589 |  },
 590 |  {
 591 |   "sentence": "['全', '部', '在', '驱', '风', '油', '，', '我', '要', '买']",
 592 |   "labeled entities": "[(3, 5, 'cp')]"
 593 |  },
 594 |  {
 595 |   "sentence": "['要', '淘', '宝', '点', '卡', '天', '宏', '一', '卡', '通', ' ', '易', '宝', '接', '口']",
 596 |   "labeled entities": "[(3, 4, 'cp'), (5, 9, 'cp')]"
 597 |  },
 598 |  {
 599 |   "sentence": "['素', '描', '本']",
 600 |   "labeled entities": "[(0, 2, 'cp')]"
 601 |  },
 602 |  {
 603 |   "sentence": "['氧', '化', '锌', '乳', '膏', '这', '个', '脸', '上', '可', '以', '用', '吗', '有', '没', '有', '激', '素']",
 604 |   "labeled entities": "[(3, 4, 'cp')]"
 605 |  },
 606 |  {
 607 |   "sentence": "['耳', '钉', '收', '纳', '架']",
 608 |   "labeled entities": "[(0, 4, 'cp')]"
 609 |  },
 610 |  {
 611 |   "sentence": "['我', '想', '找', '美', '容', '养', '颜', '，', '然', '后', '减', '肥', '的', '茶']",
 612 |   "labeled entities": "[(13, 13, 'cp')]"
 613 |  },
 614 |  {
 615 |   "sentence": "['我', '想', '找', '鞋', '柜']",
 616 |   "labeled entities": "[(3, 4, 'cp')]"
 617 |  },
 618 |  {
 619 |   "sentence": "['女', '中', '学', '生', '短', '款', '棉', '服', '薄']",
 620 |   "labeled entities": "[(6, 7, 'cp')]"
 621 |  },
 622 |  {
 623 |   "sentence": "['P', 'p', 's', 'u']",
 624 |   "labeled entities": "[]"
 625 |  },
 626 |  {
 627 |   "sentence": "['字', '母', 'k', '的', '衣', '服']",
 628 |   "labeled entities": "[(4, 5, 'cp')]"
 629 |  },
 630 |  {
 631 |   "sentence": "['荣', '耀']",
 632 |   "labeled entities": "[(0, 1, 'pp')]"
 633 |  },
 634 |  {
 635 |   "sentence": "['要', '最', '新', '款']",
 636 |   "labeled entities": "[]"
 637 |  },
 638 |  {
 639 |   "sentence": "['男', '士', '夏', '季', '上', '衣']",
 640 |   "labeled entities": "[(4, 5, 'cp')]"
 641 |  },
 642 |  {
 643 |   "sentence": "['宽', '松']",
 644 |   "labeled entities": "[]"
 645 |  },
 646 |  {
 647 |   "sentence": "['白', '色', '套', '头', '衫']",
 648 |   "labeled entities": "[(2, 4, 'cp')]"
 649 |  },
 650 |  {
 651 |   "sentence": "['全', '自', '动', '洗', '衣', '机', '9', '公', '斤']",
 652 |   "labeled entities": "[(3, 5, 'cp'), (6, 8, 'gg')]"
 653 |  },
 654 |  {
 655 |   "sentence": "['男', '唇', '膏']",
 656 |   "labeled entities": "[(1, 2, 'cp')]"
 657 |  },
 658 |  {
 659 |   "sentence": "['紧', '身', 'T', '恤', '衫', '男']",
 660 |   "labeled entities": "[(2, 4, 'cp')]"
 661 |  },
 662 |  {
 663 |   "sentence": "['意', '外', '险']",
 664 |   "labeled entities": "[(0, 2, 'cp')]"
 665 |  },
 666 |  {
 667 |   "sentence": "['我', '想', '买', '联', '系', '不', '上']",
 668 |   "labeled entities": "[]"
 669 |  },
 670 |  {
 671 |   "sentence": "['我', '想', '买', '把', '打', '鸟', '枪']",
 672 |   "labeled entities": "[(4, 6, 'cp')]"
 673 |  },
 674 |  {
 675 |   "sentence": "['请', '问', '有', '没', '有', '客', '服', '回', '答', '啊']",
 676 |   "labeled entities": "[]"
 677 |  },
 678 |  {
 679 |   "sentence": "['我', '想', '买', '小', '卷', '纸']",
 680 |   "labeled entities": "[(4, 5, 'cp')]"
 681 |  },
 682 |  {
 683 |   "sentence": "['f', 'f', 'f', '团', '常', '服']",
 684 |   "labeled entities": "[(4, 5, 'cp')]"
 685 |  },
 686 |  {
 687 |   "sentence": "['6', '0', '厘', '米', '的', '真', '皮', '女', '士', '手', '套']",
 688 |   "labeled entities": "[(0, 3, 'gg'), (9, 10, 'cp')]"
 689 |  },
 690 |  {
 691 |   "sentence": "['英', '伦', '学', '生', '鞋']",
 692 |   "labeled entities": "[(4, 4, 'cp')]"
 693 |  },
 694 |  {
 695 |   "sentence": "['需', '要', '买', '什', '么', '来', '换', '呢']",
 696 |   "labeled entities": "[]"
 697 |  },
 698 |  {
 699 |   "sentence": "['想', '问', '一', '下', '有', '没', '有', '去', '眼', '黄', '的', '眼', '药', '水']",
 700 |   "labeled entities": "[(11, 13, 'cp')]"
 701 |  },
 702 |  {
 703 |   "sentence": "['黑', '牛']",
 704 |   "labeled entities": "[]"
 705 |  },
 706 |  {
 707 |   "sentence": "['我', '想', '买', '9', '9', '0', '耳', '线']",
 708 |   "labeled entities": "[(3, 5, 'xh'), (6, 7, 'cp')]"
 709 |  },
 710 |  {
 711 |   "sentence": "['想', '买', '耐', '克', '蓝', '球', '鞋']",
 712 |   "labeled entities": "[(2, 3, 'pp'), (4, 6, 'cp')]"
 713 |  },
 714 |  {
 715 |   "sentence": "['我', '想', '泡', '水']",
 716 |   "labeled entities": "[]"
 717 |  },
 718 |  {
 719 |   "sentence": "['我', '想', '买', '一', '个', '美', '美', '的', '连', '衣', '裙']",
 720 |   "labeled entities": "[(8, 10, 'cp')]"
 721 |  },
 722 |  {
 723 |   "sentence": "['废', '柴', '修', '仙', '的', '。']",
 724 |   "labeled entities": "[]"
 725 |  },
 726 |  {
 727 |   "sentence": "['买', '连', '帽', '外', '套', '女']",
 728 |   "labeled entities": "[(3, 4, 'cp')]"
 729 |  },
 730 |  {
 731 |   "sentence": "['我', '想', '要', '投', '诉', '一', '个', '客', '服']",
 732 |   "labeled entities": "[]"
 733 |  },
 734 |  {
 735 |   "sentence": "['散', '装', '辣', '条']",
 736 |   "labeled entities": "[(2, 3, 'cp')]"
 737 |  },
 738 |  {
 739 |   "sentence": "['小', '米', '移', '动', '电', '源']",
 740 |   "labeled entities": "[(0, 1, 'pp'), (2, 5, 'cp')]"
 741 |  },
 742 |  {
 743 |   "sentence": "['吸', '引', '女', '人', '的', '男', '士', '香', '水']",
 744 |   "labeled entities": "[(7, 8, 'cp')]"
 745 |  },
 746 |  {
 747 |   "sentence": "['吃', '货', '的', '世', '界']",
 748 |   "labeled entities": "[]"
 749 |  },
 750 |  {
 751 |   "sentence": "['史', '酷', '比', '纸', '尿', '裤']",
 752 |   "labeled entities": "[(0, 2, 'pp'), (3, 5, 'cp')]"
 753 |  },
 754 |  {
 755 |   "sentence": "['简', '约', '水', '桶', '包']",
 756 |   "labeled entities": "[(2, 4, 'cp')]"
 757 |  },
 758 |  {
 759 |   "sentence": "['气', '船']",
 760 |   "labeled entities": "[(0, 1, 'cp')]"
 761 |  },
 762 |  {
 763 |   "sentence": "['德', '国', '制', '造', '的', '新', '发', '明']",
 764 |   "labeled entities": "[]"
 765 |  },
 766 |  {
 767 |   "sentence": "['平', '价', '眼', '影']",
 768 |   "labeled entities": "[(2, 3, 'cp')]"
 769 |  },
 770 |  {
 771 |   "sentence": "['胃', '不', '好', '，', '想', '买', '点', '利', '于', '消', '化', '的', '药']",
 772 |   "labeled entities": "[(12, 12, 'cp')]"
 773 |  },
 774 |  {
 775 |   "sentence": "['送', '女', '士', '生', '日', '礼', '物', '送', '啥', '好']",
 776 |   "labeled entities": "[]"
 777 |  },
 778 |  {
 779 |   "sentence": "['百', '灵', '草', '修', '复', '霜']",
 780 |   "labeled entities": "[(3, 5, 'cp')]"
 781 |  },
 782 |  {
 783 |   "sentence": "['帮', '我', '推', '荐', '一', '些', '情', '侣', 'T', '恤']",
 784 |   "labeled entities": "[(8, 9, 'cp')]"
 785 |  },
 786 |  {
 787 |   "sentence": "['要', '买', '去', '唇', '部', '死', '皮', '的']",
 788 |   "labeled entities": "[]"
 789 |  },
 790 |  {
 791 |   "sentence": "['买', '墨', '水', '笔', '座']",
 792 |   "labeled entities": "[(3, 4, 'cp')]"
 793 |  },
 794 |  {
 795 |   "sentence": "['我', '要', '找', '闲', '鱼', '网']",
 796 |   "labeled entities": "[]"
 797 |  },
 798 |  {
 799 |   "sentence": "['给', '爸', '妈', '送', '礼', '物', '，', '送', '什', '么', '好', '呢', '？']",
 800 |   "labeled entities": "[]"
 801 |  },
 802 |  {
 803 |   "sentence": "['我', '要', '买', '保', '鲜', '袋', '小', '号']",
 804 |   "labeled entities": "[(3, 5, 'cp')]"
 805 |  },
 806 |  {
 807 |   "sentence": "['口', '紅']",
 808 |   "labeled entities": "[(0, 1, 'cp')]"
 809 |  },
 810 |  {
 811 |   "sentence": "['我', '要', '买', '婴', '儿', '洗', '头']",
 812 |   "labeled entities": "[]"
 813 |  },
 814 |  {
 815 |   "sentence": "['我', '要', '买', '婴', '儿', '粉']",
 816 |   "labeled entities": "[(3, 5, 'cp')]"
 817 |  },
 818 |  {
 819 |   "sentence": "['我', '要', '买', 'j', 'o', 'y', 'f', 'i', 's', 'h']",
 820 |   "labeled entities": "[(3, 9, 'pp')]"
 821 |  },
 822 |  {
 823 |   "sentence": "['披', '萨', '饼', '底', '8', '寸', '多', '少', '钱']",
 824 |   "labeled entities": "[(0, 3, 'cp'), (4, 5, 'gg')]"
 825 |  },
 826 |  {
 827 |   "sentence": "['我', '要', '买', '厨', '房', '用', '纸']",
 828 |   "labeled entities": "[(3, 6, 'cp')]"
 829 |  },
 830 |  {
 831 |   "sentence": "['我', '要', '买', '腋', '下', '止', '汗', '喷', '雾', ' ', '香', '体', '露', ' ', '男', '士']",
 832 |   "labeled entities": "[(5, 8, 'cp'), (10, 12, 'cp')]"
 833 |  },
 834 |  {
 835 |   "sentence": "['护', '垫', '护', '舒', '宝', '多', '少', '钱']",
 836 |   "labeled entities": "[(0, 1, 'cp'), (2, 4, 'pp')]"
 837 |  },
 838 |  {
 839 |   "sentence": "['我', '要', '买', '三', '只', '松', '鼠', ' ', '坚', '果', ' ', '大', '礼', '包']",
 840 |   "labeled entities": "[(3, 6, 'pp'), (8, 9, 'cp')]"
 841 |  },
 842 |  {
 843 |   "sentence": "['乐', '而', '雅', '多', '少', '钱']",
 844 |   "labeled entities": "[(0, 2, 'pp')]"
 845 |  },
 846 |  {
 847 |   "sentence": "['我', '要', '买', '真', '知', '棒', '棒', '棒', '糖']",
 848 |   "labeled entities": "[(3, 5, 'pp'), (6, 8, 'cp')]"
 849 |  },
 850 |  {
 851 |   "sentence": "['我', '要', '买', '好', '奇', '铂', '金', '装', 'm']",
 852 |   "labeled entities": "[(3, 4, 'pp'), (5, 7, 'xh'), (8, 8, 'gg')]"
 853 |  },
 854 |  {
 855 |   "sentence": "['我', '要', '买', '筷', '子', ' ', '勺', '子']",
 856 |   "labeled entities": "[(3, 4, 'cp'), (6, 7, 'cp')]"
 857 |  },
 858 |  {
 859 |   "sentence": "['我', '要', '买', '办', '公']",
 860 |   "labeled entities": "[]"
 861 |  },
 862 |  {
 863 |   "sentence": "['我', '要', '买', '良', '品', '铺', '子', '榴', '莲', '干']",
 864 |   "labeled entities": "[(3, 6, 'pp'), (7, 9, 'cp')]"
 865 |  },
 866 |  {
 867 |   "sentence": "['海', '尔', '电', '视', '多', '少', '钱']",
 868 |   "labeled entities": "[(0, 1, 'pp'), (2, 3, 'cp')]"
 869 |  },
 870 |  {
 871 |   "sentence": "['我', '要', '买', '卫', '生', '巾', ' ', '2', '9', '0']",
 872 |   "labeled entities": "[(3, 5, 'cp')]"
 873 |  },
 874 |  {
 875 |   "sentence": "['买', '显', '卡']",
 876 |   "labeled entities": "[(1, 2, 'cp')]"
 877 |  },
 878 |  {
 879 |   "sentence": "['我', '要', '买', '新', '安', '怡', '安', '抚', '奶', '嘴']",
 880 |   "labeled entities": "[(3, 5, 'pp'), (6, 9, 'cp')]"
 881 |  },
 882 |  {
 883 |   "sentence": "['我', '要', '买', '枪', '手', '杀', '虫', '气', '雾', '剂']",
 884 |   "labeled entities": "[(3, 4, 'pp'), (5, 9, 'cp')]"
 885 |  },
 886 |  {
 887 |   "sentence": "['鸭', '脖']",
 888 |   "labeled entities": "[(0, 1, 'cp')]"
 889 |  },
 890 |  {
 891 |   "sentence": "['我', '要', '买', '艾', '艾', '贴']",
 892 |   "labeled entities": "[(3, 5, 'cp')]"
 893 |  },
 894 |  {
 895 |   "sentence": "['我', '要', '买', '产', '妇', '帽']",
 896 |   "labeled entities": "[(3, 5, 'cp')]"
 897 |  },
 898 |  {
 899 |   "sentence": "['博', '朗', '多', '少', '钱']",
 900 |   "labeled entities": "[(0, 1, 'pp')]"
 901 |  },
 902 |  {
 903 |   "sentence": "['我', '要', '买', '海', '天', '招', '牌', '拌', '饭', '酱']",
 904 |   "labeled entities": "[(3, 4, 'pp'), (7, 9, 'cp')]"
 905 |  },
 906 |  {
 907 |   "sentence": "['我', '要', '买', '爱', '护', '湿', '巾']",
 908 |   "labeled entities": "[(3, 4, 'pp'), (5, 6, 'cp')]"
 909 |  },
 910 |  {
 911 |   "sentence": "['我', '要', '买', '粉', '刺', '针', '黑', '头', '针']",
 912 |   "labeled entities": "[(3, 5, 'cp'), (6, 8, 'cp')]"
 913 |  },
 914 |  {
 915 |   "sentence": "['我', '要', '的', '是', '面', '膜']",
 916 |   "labeled entities": "[(4, 5, 'cp')]"
 917 |  },
 918 |  {
 919 |   "sentence": "['我', '要', '买', '头', '发', '定', '型']",
 920 |   "labeled entities": "[]"
 921 |  },
 922 |  {
 923 |   "sentence": "['我', '要', '买', '水', '笔', ' ', '中', '性', '笔']",
 924 |   "labeled entities": "[(3, 4, 'cp'), (6, 8, 'cp')]"
 925 |  },
 926 |  {
 927 |   "sentence": "['干', '燥', '剂', '多', '少', '钱']",
 928 |   "labeled entities": "[(0, 2, 'cp')]"
 929 |  },
 930 |  {
 931 |   "sentence": "['船', '袜', '男', '多', '少', '钱']",
 932 |   "labeled entities": "[(0, 1, 'cp')]"
 933 |  },
 934 |  {
 935 |   "sentence": "['我', '要', '买', '学', '步', '裤']",
 936 |   "labeled entities": "[(3, 5, 'cp')]"
 937 |  },
 938 |  {
 939 |   "sentence": "['海', '鸭', '蛋', '多', '少', '钱']",
 940 |   "labeled entities": "[(0, 2, 'cp')]"
 941 |  },
 942 |  {
 943 |   "sentence": "['我', '要', '买', '东', '古']",
 944 |   "labeled entities": "[(3, 4, 'pp')]"
 945 |  },
 946 |  {
 947 |   "sentence": "['我', '要', '买', '鲁', '花', '葵', '花', '籽', '油']",
 948 |   "labeled entities": "[(3, 4, 'pp'), (5, 8, 'cp')]"
 949 |  },
 950 |  {
 951 |   "sentence": "['我', '要', '买', '妮', '维', '雅', '走', '珠']",
 952 |   "labeled entities": "[(3, 5, 'pp'), (6, 7, 'cp')]"
 953 |  },
 954 |  {
 955 |   "sentence": "['我', '要', '买', '女', '鞋', '拖']",
 956 |   "labeled entities": "[(4, 5, 'cp')]"
 957 |  },
 958 |  {
 959 |   "sentence": "['我', '要', '买', '老', '干', '妈', '牛', '肉', '酱']",
 960 |   "labeled entities": "[(3, 5, 'pp'), (6, 8, 'cp')]"
 961 |  },
 962 |  {
 963 |   "sentence": "['文', '胸', '袋', '洗', '内', '衣', '专', '用', '洗', '衣', '袋', '网', '袋', '多', '少', '钱']",
 964 |   "labeled entities": "[(0, 2, 'cp'), (8, 10, 'cp'), (11, 12, 'cp')]"
 965 |  },
 966 |  {
 967 |   "sentence": "['我', '要', '买', '安', '安', '金', '纯', '沐', '浴', '露']",
 968 |   "labeled entities": "[(3, 6, 'pp'), (7, 9, 'cp')]"
 969 |  },
 970 |  {
 971 |   "sentence": "['雪', '融', '芝', '士', '多', '少', '钱']",
 972 |   "labeled entities": "[(0, 3, 'cp')]"
 973 |  },
 974 |  {
 975 |   "sentence": "['拉', '拉', '裤', 'x', 'x', 'x', 'l', '多', '少', '钱']",
 976 |   "labeled entities": "[(0, 2, 'cp'), (3, 6, 'gg')]"
 977 |  },
 978 |  {
 979 |   "sentence": "['墨', '鱼', '丸', '多', '少', '钱']",
 980 |   "labeled entities": "[(0, 2, 'cp')]"
 981 |  },
 982 |  {
 983 |   "sentence": "['小', '肥', '羊', '多', '少', '钱']",
 984 |   "labeled entities": "[(0, 2, 'pp')]"
 985 |  },
 986 |  {
 987 |   "sentence": "['我', '要', '买', '无', '糖', '王', '老', '吉']",
 988 |   "labeled entities": "[(5, 7, 'cp')]"
 989 |  },
 990 |  {
 991 |   "sentence": "['我', '要', '买', '美', '发', '梳', '子']",
 992 |   "labeled entities": "[(5, 6, 'cp')]"
 993 |  },
 994 |  {
 995 |   "sentence": "['我', '要', '买', '桌', '面']",
 996 |   "labeled entities": "[(3, 4, 'cp')]"
 997 |  },
 998 |  {
 999 |   "sentence": "['熊', '孩', '子', '食', '品', '多', '少', '钱']",
1000 |   "labeled entities": "[(0, 2, 'pp'), (3, 4, 'cp')]"
1001 |  },
1002 |  {
1003 |   "sentence": "['我', '要', '买', '双', '汇', '鸡', '肉', '肠']",
1004 |   "labeled entities": "[(3, 4, 'pp'), (5, 7, 'cp')]"
1005 |  },
1006 |  {
1007 |   "sentence": "['我', '要', '买', '红', '茶', '茶', '叶']",
1008 |   "labeled entities": "[(3, 6, 'cp')]"
1009 |  },
1010 |  {
1011 |   "sentence": "['洗', '衣', '液', '绿', '伞', '多', '少', '钱']",
1012 |   "labeled entities": "[(0, 2, 'cp'), (3, 4, 'pp')]"
1013 |  },
1014 |  {
1015 |   "sentence": "['我', '要', '买', '深', '层', '清', '洁', '洗', '面', '奶']",
1016 |   "labeled entities": "[(7, 9, 'cp')]"
1017 |  },
1018 |  {
1019 |   "sentence": "['买', '裙', '子']",
1020 |   "labeled entities": "[(1, 2, 'cp')]"
1021 |  },
1022 |  {
1023 |   "sentence": "['脆', '骨', '烤', '肠', '多', '少', '钱']",
1024 |   "labeled entities": "[(0, 3, 'cp')]"
1025 |  },
1026 |  {
1027 |   "sentence": "['大', '米', '5', 'k', 'g', ' ', '天', '猫', '超', '市', '多', '少', '钱']",
1028 |   "labeled entities": "[(0, 1, 'cp'), (2, 4, 'gg')]"
1029 |  },
1030 |  {
1031 |   "sentence": "['我', '要', '买', '牙', '杯', '洗', '漱', '杯']",
1032 |   "labeled entities": "[(3, 4, 'cp'), (5, 7, 'cp')]"
1033 |  },
1034 |  {
1035 |   "sentence": "['我', '要', '买', '化', '妆', '品', '套', '装']",
1036 |   "labeled entities": "[(3, 5, 'cp'), (6, 7, 'cp')]"
1037 |  },
1038 |  {
1039 |   "sentence": "['我', '要', '买', '炒', '菜', '铲', '子']",
1040 |   "labeled entities": "[(3, 6, 'cp')]"
1041 |  },
1042 |  {
1043 |   "sentence": "['番', '茄', '酱', ' ', '亨', '氏', '多', '少', '钱']",
1044 |   "labeled entities": "[(0, 2, 'cp'), (4, 5, 'pp')]"
1045 |  },
1046 |  {
1047 |   "sentence": "['我', '要', '买', '利', '达']",
1048 |   "labeled entities": "[(3, 4, 'pp')]"
1049 |  },
1050 |  {
1051 |   "sentence": "['我', '要', '买', '英', '氏', '宝', '宝', '肉', '松', '辅', '食', ' ', '婴', '儿', '肉', '松', '牛', '肉', '松']",
1052 |   "labeled entities": "[(3, 4, 'pp'), (5, 8, 'cp'), (12, 15, 'cp'), (16, 18, 'cp')]"
1053 |  },
1054 |  {
1055 |   "sentence": "['婴', '儿', '面', '条', '宝', '宝', '辅', '食', '蝴', '蝶', '面', '多', '少', '钱']",
1056 |   "labeled entities": "[(0, 3, 'cp'), (4, 7, 'cp'), (8, 10, 'cp')]"
1057 |  },
1058 |  {
1059 |   "sentence": "['我', '要', '买', '韩', '国', '辣', '椒', '酱']",
1060 |   "labeled entities": "[(5, 7, 'cp')]"
1061 |  },
1062 |  {
1063 |   "sentence": "['无', '糖', '食', '品', '多', '少', '钱']",
1064 |   "labeled entities": "[(0, 3, 'cp')]"
1065 |  },
1066 |  {
1067 |   "sentence": "['心', '心', '相', '印', '湿', '巾', '多', '少', '钱']",
1068 |   "labeled entities": "[(0, 3, 'pp'), (4, 5, 'cp')]"
1069 |  },
1070 |  {
1071 |   "sentence": "['連', '衣', '裙']",
1072 |   "labeled entities": "[(0, 2, 'cp')]"
1073 |  },
1074 |  {
1075 |   "sentence": "['呀', '土', '豆', '4', '0', 'g', '多', '少', '钱']",
1076 |   "labeled entities": "[(0, 2, 'cp'), (3, 5, 'gg')]"
1077 |  },
1078 |  {
1079 |   "sentence": "['我', '要', '买', '麦', '片', '金', '味']",
1080 |   "labeled entities": "[(3, 4, 'cp'), (5, 6, 'pp')]"
1081 |  },
1082 |  {
1083 |   "sentence": "['格', '力', '变', '频', '空', '调', '多', '少', '钱']",
1084 |   "labeled entities": "[(0, 1, 'pp'), (2, 5, 'cp')]"
1085 |  },
1086 |  {
1087 |   "sentence": "['鸭', '血', '多', '少', '钱']",
1088 |   "labeled entities": "[(0, 1, 'cp')]"
1089 |  },
1090 |  {
1091 |   "sentence": "['籼', '米', '多', '少', '钱']",
1092 |   "labeled entities": "[(0, 1, 'cp')]"
1093 |  },
1094 |  {
1095 |   "sentence": "['塔', '塔', '粉', '多', '少', '钱']",
1096 |   "labeled entities": "[(0, 2, 'cp')]"
1097 |  },
1098 |  {
1099 |   "sentence": "['袜', '子', ' ', '女', ' ', '船', '袜', '多', '少', '钱']",
1100 |   "labeled entities": "[(0, 1, 'cp'), (5, 6, 'cp')]"
1101 |  },
1102 |  {
1103 |   "sentence": "['我', '要', '买', '电', '动', '刷', '头']",
1104 |   "labeled entities": "[(3, 6, 'cp')]"
1105 |  },
1106 |  {
1107 |   "sentence": "['红', '色', '小', '象', '多', '少', '钱']",
1108 |   "labeled entities": "[(0, 3, 'pp')]"
1109 |  },
1110 |  {
1111 |   "sentence": "['我', '要', '买', '兔', '肉']",
1112 |   "labeled entities": "[(3, 4, 'cp')]"
1113 |  },
1114 |  {
1115 |   "sentence": "['我', '要', '买', '纯', '木', '植', '护']",
1116 |   "labeled entities": "[(3, 6, 'cp')]"
1117 |  },
1118 |  {
1119 |   "sentence": "['艾', '诗', '多', '少', '钱']",
1120 |   "labeled entities": "[(0, 1, 'pp')]"
1121 |  },
1122 |  {
1123 |   "sentence": "['熏', '肉', '多', '少', '钱']",
1124 |   "labeled entities": "[(0, 1, 'cp')]"
1125 |  },
1126 |  {
1127 |   "sentence": "['我', '要', '买', '洗', '头', '水', '女']",
1128 |   "labeled entities": "[(3, 5, 'cp')]"
1129 |  },
1130 |  {
1131 |   "sentence": "['蓝', '泡', '泡', '洁', '厕', '宝', '多', '少', '钱']",
1132 |   "labeled entities": "[(0, 2, 'cp'), (3, 5, 'cp')]"
1133 |  },
1134 |  {
1135 |   "sentence": "['加', '加', '生', '抽', '多', '少', '钱']",
1136 |   "labeled entities": "[(0, 1, 'pp'), (2, 3, 'cp')]"
1137 |  },
1138 |  {
1139 |   "sentence": "['爱', '生', '活', '多', '少', '钱']",
1140 |   "labeled entities": "[(0, 2, 'pp')]"
1141 |  },
1142 |  {
1143 |   "sentence": "['全', '脂', '奶', '粉']",
1144 |   "labeled entities": "[(0, 3, 'cp')]"
1145 |  },
1146 |  {
1147 |   "sentence": "['我', '要', '买', '美', '素']",
1148 |   "labeled entities": "[(3, 4, 'pp')]"
1149 |  },
1150 |  {
1151 |   "sentence": "['我', '要', '买', '全', '面', '时', '代']",
1152 |   "labeled entities": "[(3, 6, 'pp')]"
1153 |  },
1154 |  {
1155 |   "sentence": "['我', '要', '买', '好', '爸', '爸', '洗', '衣', '皂']",
1156 |   "labeled entities": "[(3, 5, 'pp'), (6, 8, 'cp')]"
1157 |  },
1158 |  {
1159 |   "sentence": "['我', '要', '买', '酸', '奶', '发', '酵', '菌', '1', '0', '菌', '双', '歧', '杆', '菌', '益', '生', '菌', '粉']",
1160 |   "labeled entities": "[(3, 4, 'cp'), (15, 18, 'cp')]"
1161 |  },
1162 |  {
1163 |   "sentence": "['我', '要', '买', '丝', '蕴', '套', '装']",
1164 |   "labeled entities": "[(3, 4, 'pp'), (5, 6, 'cp')]"
1165 |  },
1166 |  {
1167 |   "sentence": "['金', '星', '啤', '酒', '多', '少', '钱']",
1168 |   "labeled entities": "[(0, 1, 'pp'), (2, 3, 'cp')]"
1169 |  },
1170 |  {
1171 |   "sentence": "['美', '式', '咖', '啡', '多', '少', '钱']",
1172 |   "labeled entities": "[(0, 3, 'cp')]"
1173 |  },
1174 |  {
1175 |   "sentence": "['我', '要', '买', '毛', '巾', '纱', '布']",
1176 |   "labeled entities": "[(3, 4, 'cp'), (5, 6, 'cp')]"
1177 |  },
1178 |  {
1179 |   "sentence": "['婴', '儿', '爽', '身', '粉', '多', '少', '钱']",
1180 |   "labeled entities": "[(0, 4, 'cp')]"
1181 |  },
1182 |  {
1183 |   "sentence": "['康', '元', '手', '指', '饼', '干', '多', '少', '钱']",
1184 |   "labeled entities": "[(0, 1, 'pp'), (2, 5, 'cp')]"
1185 |  },
1186 |  {
1187 |   "sentence": "['木', '头', '勺', '子', '多', '少', '钱']",
1188 |   "labeled entities": "[(2, 3, 'cp')]"
1189 |  },
1190 |  {
1191 |   "sentence": "['灭', '蚊', '灯', '多', '少', '钱']",
1192 |   "labeled entities": "[(0, 2, 'cp')]"
1193 |  },
1194 |  {
1195 |   "sentence": "['水', '果', '牙', '签', '多', '少', '钱']",
1196 |   "labeled entities": "[(0, 3, 'cp')]"
1197 |  },
1198 |  {
1199 |   "sentence": "['椰', '浆', '多', '少', '钱']",
1200 |   "labeled entities": "[(0, 1, 'cp')]"
1201 |  },
1202 |  {
1203 |   "sentence": "['我', '要', '买', '好', '奇', '铂', '金', '装', 'n', 'b']",
1204 |   "labeled entities": "[(3, 4, 'pp'), (5, 7, 'xh'), (8, 9, 'gg')]"
1205 |  },
1206 |  {
1207 |   "sentence": "['益', '昌', '多', '少', '钱']",
1208 |   "labeled entities": "[(0, 1, 'pp')]"
1209 |  },
1210 |  {
1211 |   "sentence": "['牛', '奶', ' ', '光', '明', '多', '少', '钱']",
1212 |   "labeled entities": "[(0, 1, 'cp'), (3, 4, 'pp')]"
1213 |  },
1214 |  {
1215 |   "sentence": "['舒', '适', '达', '美', '白', '配', '方', '抗', '敏', '感', '牙', '膏', '多', '少', '钱']",
1216 |   "labeled entities": "[(0, 2, 'pp'), (10, 11, 'cp')]"
1217 |  },
1218 |  {
1219 |   "sentence": "['我', '要', '买', '辣', '的', '零', '食']",
1220 |   "labeled entities": "[(5, 6, 'cp')]"
1221 |  },
1222 |  {
1223 |   "sentence": "['葱', '油', '花', '卷', '多', '少', '钱']",
1224 |   "labeled entities": "[(0, 3, 'cp')]"
1225 |  },
1226 |  {
1227 |   "sentence": "['我', '要', '买', '肉', '枣']",
1228 |   "labeled entities": "[(3, 4, 'cp')]"
1229 |  },
1230 |  {
1231 |   "sentence": "['凉', '水', '多', '少', '钱']",
1232 |   "labeled entities": "[(0, 1, 'cp')]"
1233 |  },
1234 |  {
1235 |   "sentence": "['梦', '之', '蓝', 'm', '3', '多', '少', '钱']",
1236 |   "labeled entities": "[(0, 2, 'cp'), (3, 4, 'xh')]"
1237 |  },
1238 |  {
1239 |   "sentence": "['我', '要', '买', '惠', '氏', '启', '赋', '1', '段']",
1240 |   "labeled entities": "[(3, 4, 'pp'), (5, 6, 'xh')]"
1241 |  },
1242 |  {
1243 |   "sentence": "['君', '乐', '宝', '纯', '牛', '奶', '多', '少', '钱']",
1244 |   "labeled entities": "[(0, 2, 'pp'), (3, 5, 'cp')]"
1245 |  },
1246 |  {
1247 |   "sentence": "['脆', '面', '多', '少', '钱']",
1248 |   "labeled entities": "[(0, 1, 'cp')]"
1249 |  },
1250 |  {
1251 |   "sentence": "['我', '要', '买', '雀', '巢', '威', '化', '巧', '克', '力']",
1252 |   "labeled entities": "[(3, 4, 'pp'), (5, 9, 'cp')]"
1253 |  },
1254 |  {
1255 |   "sentence": "['烟', '灰', '缸', '家', '用', '多', '少', '钱']",
1256 |   "labeled entities": "[(0, 2, 'cp')]"
1257 |  },
1258 |  {
1259 |   "sentence": "['我', '要', '买', '牙', '膏', '牙', '刷', '套', '装']",
1260 |   "labeled entities": "[(3, 4, 'cp'), (5, 6, 'cp'), (7, 8, 'cp')]"
1261 |  },
1262 |  {
1263 |   "sentence": "['我', '要', '买', '席', '子']",
1264 |   "labeled entities": "[(3, 4, 'cp')]"
1265 |  },
1266 |  {
1267 |   "sentence": "['荷', '兰', '乳', '牛', '多', '少', '钱']",
1268 |   "labeled entities": "[(0, 3, 'cp')]"
1269 |  },
1270 |  {
1271 |   "sentence": "['百', '加', '得', '黑', '朗', '姆', '酒', '多', '少', '钱']",
1272 |   "labeled entities": "[(0, 2, 'pp'), (3, 6, 'cp')]"
1273 |  },
1274 |  {
1275 |   "sentence": "['儿', '童', '碗', '餐', '具', '防', '摔', '多', '少', '钱']",
1276 |   "labeled entities": "[(0, 2, 'cp'), (3, 4, 'cp')]"
1277 |  },
1278 |  {
1279 |   "sentence": "['我', '要', '买', '进', '口', '牛', '奶', '2', '5', '0', 'm', 'l']",
1280 |   "labeled entities": "[(5, 6, 'cp'), (7, 11, 'gg')]"
1281 |  },
1282 |  {
1283 |   "sentence": "['启', '初', '婴', '儿', '保', '湿', '露', '多', '少', '钱']",
1284 |   "labeled entities": "[(0, 1, 'pp'), (2, 6, 'cp')]"
1285 |  },
1286 |  {
1287 |   "sentence": "['我', '要', '买', '米', '奇']",
1288 |   "labeled entities": "[]"
1289 |  },
1290 |  {
1291 |   "sentence": "['我', '要', '买', '莲', '子']",
1292 |   "labeled entities": "[(3, 4, 'cp')]"
1293 |  },
1294 |  {
1295 |   "sentence": "['我', '要', '买', '咯', '吱', '脆']",
1296 |   "labeled entities": "[(3, 5, 'xh')]"
1297 |  },
1298 |  {
1299 |   "sentence": "['奶', '粉', '三', '段', '多', '少', '钱']",
1300 |   "labeled entities": "[(0, 1, 'cp')]"
1301 |  },
1302 |  {
1303 |   "sentence": "['我', '要', '买', '豆', '沙', '粽', '子']",
1304 |   "labeled entities": "[(3, 6, 'cp')]"
1305 |  },
1306 |  {
1307 |   "sentence": "['我', '要', '买', '乐', '视', '手', '机']",
1308 |   "labeled entities": "[(3, 4, 'pp'), (5, 6, 'cp')]"
1309 |  },
1310 |  {
1311 |   "sentence": "['厦', '门', '泡', '面', '多', '少', '钱']",
1312 |   "labeled entities": "[(0, 1, 'pp'), (2, 3, 'cp')]"
1313 |  },
1314 |  {
1315 |   "sentence": "['我', '要', '买', '罐']",
1316 |   "labeled entities": "[(3, 3, 'cp')]"
1317 |  },
1318 |  {
1319 |   "sentence": "['卫', '生', '巾', '超', '市', '多', '少', '钱']",
1320 |   "labeled entities": "[(0, 2, 'cp')]"
1321 |  },
1322 |  {
1323 |   "sentence": "['麦', '吉', '士', '山', '核', '桃', '小', '酥', '多', '少', '钱']",
1324 |   "labeled entities": "[(0, 2, 'pp'), (3, 7, 'cp')]"
1325 |  },
1326 |  {
1327 |   "sentence": "['我', '要', '买', '披', '萨', '芝', '士']",
1328 |   "labeled entities": "[(3, 4, 'cp'), (5, 6, 'cp')]"
1329 |  },
1330 |  {
1331 |   "sentence": "['泡', '面', '锅', '多', '少', '钱']",
1332 |   "labeled entities": "[(0, 2, 'cp')]"
1333 |  },
1334 |  {
1335 |   "sentence": "['破', '洞', '牛', '仔', '裤']",
1336 |   "labeled entities": "[(2, 4, 'cp')]"
1337 |  },
1338 |  {
1339 |   "sentence": "['凉', '粉', ' ', '仙', '草', '多', '少', '钱']",
1340 |   "labeled entities": "[(0, 1, 'cp'), (3, 4, 'cp')]"
1341 |  },
1342 |  {
1343 |   "sentence": "['我', '要', '买', '按', '摩', '椅']",
1344 |   "labeled entities": "[(3, 5, 'cp')]"
1345 |  },
1346 |  {
1347 |   "sentence": "['短', '袖', '多', '少', '钱']",
1348 |   "labeled entities": "[]"
1349 |  },
1350 |  {
1351 |   "sentence": "['我', '要', '买', '密', '码', '箱']",
1352 |   "labeled entities": "[(3, 5, 'cp')]"
1353 |  },
1354 |  {
1355 |   "sentence": "['我', '要', '买', '安', '儿', '乐', 'x', 'l']",
1356 |   "labeled entities": "[(3, 5, 'pp'), (6, 7, 'gg')]"
1357 |  },
1358 |  {
1359 |   "sentence": "['我', '要', '买', '维']",
1360 |   "labeled entities": "[]"
1361 |  },
1362 |  {
1363 |   "sentence": "['我', '要', '买', '薯', '片', '黄', '瓜']",
1364 |   "labeled entities": "[(3, 4, 'cp')]"
1365 |  },
1366 |  {
1367 |   "sentence": "['我', '要', '买', '菜', '板', '抗', '菌']",
1368 |   "labeled entities": "[(3, 4, 'cp')]"
1369 |  },
1370 |  {
1371 |   "sentence": "['方', '便', '面', ' ', '酸', '豆', '角', '多', '少', '钱']",
1372 |   "labeled entities": "[(0, 2, 'cp'), (4, 6, 'cp')]"
1373 |  },
1374 |  {
1375 |   "sentence": "['罗', '马', '仕']",
1376 |   "labeled entities": "[(0, 2, 'pp')]"
1377 |  },
1378 |  {
1379 |   "sentence": "['我', '要', '买', '有', '友', '猪', '皮']",
1380 |   "labeled entities": "[(3, 4, 'pp'), (5, 6, 'cp')]"
1381 |  },
1382 |  {
1383 |   "sentence": "['染', '发', '剂', ' ', '欧', '莱', '雅', '多', '少', '钱']",
1384 |   "labeled entities": "[(0, 2, 'cp'), (4, 6, 'pp')]"
1385 |  },
1386 |  {
1387 |   "sentence": "['学', '步', '多', '少', '钱']",
1388 |   "labeled entities": "[]"
1389 |  },
1390 |  {
1391 |   "sentence": "['我', '要', '买', '襄', '阳', '卧', '龙', '锅', '巴']",
1392 |   "labeled entities": "[(5, 6, 'pp'), (7, 8, 'cp')]"
1393 |  },
1394 |  {
1395 |   "sentence": "['贝', '奇', '野', '菜', '多', '少', '钱']",
1396 |   "labeled entities": "[(0, 3, 'cp')]"
1397 |  },
1398 |  {
1399 |   "sentence": "['广', '东', '潮', '汕', '特', '产', '多', '少', '钱']",
1400 |   "labeled entities": "[]"
1401 |  },
1402 |  {
1403 |   "sentence": "['哺', '乳', '衣']",
1404 |   "labeled entities": "[(0, 2, 'cp')]"
1405 |  },
1406 |  {
1407 |   "sentence": "['好', '奇', 'm', '多', '少', '钱']",
1408 |   "labeled entities": "[(0, 1, 'pp'), (2, 2, 'gg')]"
1409 |  },
1410 |  {
1411 |   "sentence": "['漂', '亮', '连', '衣', '裙']",
1412 |   "labeled entities": "[(2, 4, 'cp')]"
1413 |  },
1414 |  {
1415 |   "sentence": "['我', '要', '买', '笔', '记', '本']",
1416 |   "labeled entities": "[(3, 5, 'cp')]"
1417 |  },
1418 |  {
1419 |   "sentence": "['我', '要', '买', '人', '参']",
1420 |   "labeled entities": "[(3, 4, 'cp')]"
1421 |  },
1422 |  {
1423 |   "sentence": "['李', '锦', '记', '醋', '多', '少', '钱']",
1424 |   "labeled entities": "[(0, 2, 'pp'), (3, 3, 'cp')]"
1425 |  },
1426 |  {
1427 |   "sentence": "['我', '要', '买', '洽', '洽', '小', '而', '香', '西', '瓜', '子']",
1428 |   "labeled entities": "[(3, 4, 'pp'), (5, 7, 'xh'), (8, 10, 'cp')]"
1429 |  },
1430 |  {
1431 |   "sentence": "['纱', '布', '毛', '巾', '多', '少', '钱']",
1432 |   "labeled entities": "[(2, 3, 'cp')]"
1433 |  },
1434 |  {
1435 |   "sentence": "['我', '要', '买', '豆', '腐', '皮']",
1436 |   "labeled entities": "[(3, 5, 'cp')]"
1437 |  },
1438 |  {
1439 |   "sentence": "['水', '瓶', '多', '少', '钱']",
1440 |   "labeled entities": "[(0, 1, 'cp')]"
1441 |  },
1442 |  {
1443 |   "sentence": "['沐', '浴', '露']",
1444 |   "labeled entities": "[(0, 2, 'cp')]"
1445 |  },
1446 |  {
1447 |   "sentence": "['我', '要', '买', '猪', '鼻', '贴']",
1448 |   "labeled entities": "[(3, 5, 'cp')]"
1449 |  },
1450 |  {
1451 |   "sentence": "['百', '草', '味', '爆', '米', '花', '多', '少', '钱']",
1452 |   "labeled entities": "[(0, 2, 'pp'), (3, 5, 'cp')]"
1453 |  },
1454 |  {
1455 |   "sentence": "['我', '要', '买', '一', '次', '性', '口', '罩']",
1456 |   "labeled entities": "[(3, 7, 'cp')]"
1457 |  },
1458 |  {
1459 |   "sentence": "['我', '要', '买', '广', '东', '特', '产']",
1460 |   "labeled entities": "[(3, 6, 'cp')]"
1461 |  },
1462 |  {
1463 |   "sentence": "['我', '要', '买', '富', '安', '娜']",
1464 |   "labeled entities": "[(3, 5, 'pp')]"
1465 |  },
1466 |  {
1467 |   "sentence": "['我', '要', '买', '胶', '棉', '拖', '把', '头']",
1468 |   "labeled entities": "[(5, 7, 'cp')]"
1469 |  },
1470 |  {
1471 |   "sentence": "['养', '元', '青', '洗', '发', '水', '多', '少', '钱']",
1472 |   "labeled entities": "[(0, 2, 'pp'), (3, 5, 'cp')]"
1473 |  },
1474 |  {
1475 |   "sentence": "['我', '要', '买', '雄', '鸡', '标']",
1476 |   "labeled entities": "[(3, 5, 'pp')]"
1477 |  },
1478 |  {
1479 |   "sentence": "['我', '要', '买', '海', '苔', '薄', '脆', '饼', '干']",
1480 |   "labeled entities": "[(5, 8, 'cp')]"
1481 |  },
1482 |  {
1483 |   "sentence": "['我', '要', '买', '生', '鲜', '肉', '类']",
1484 |   "labeled entities": "[(3, 6, 'cp')]"
1485 |  },
1486 |  {
1487 |   "sentence": "['洗', '内', '衣', '多', '少', '钱']",
1488 |   "labeled entities": "[(1, 2, 'cp')]"
1489 |  },
1490 |  {
1491 |   "sentence": "['我', '要', '买', '冰', '淇', '淋', '雪', '糕']",
1492 |   "labeled entities": "[(3, 5, 'cp'), (6, 7, 'cp')]"
1493 |  },
1494 |  {
1495 |   "sentence": "['我', '要', '买', '不', '锈', '钢', '饭', '盒']",
1496 |   "labeled entities": "[(6, 7, 'cp')]"
1497 |  },
1498 |  {
1499 |   "sentence": "['帮', '宝', '适', '拉', '拉', '裤', 'x', 'x', 'l', '多', '少', '钱']",
1500 |   "labeled entities": "[(0, 2, 'pp'), (3, 5, 'cp'), (6, 8, 'gg')]"
1501 |  },
1502 |  {
1503 |   "sentence": "['美', '素', '佳', '儿', '多', '少', '钱']",
1504 |   "labeled entities": "[(0, 3, 'pp')]"
1505 |  },
1506 |  {
1507 |   "sentence": "['我', '要', '买', '抑', '汗']",
1508 |   "labeled entities": "[]"
1509 |  },
1510 |  {
1511 |   "sentence": "['洗', '面', '奶', '旅', '行', '装', '多', '少', '钱']",
1512 |   "labeled entities": "[(0, 2, 'cp')]"
1513 |  },
1514 |  {
1515 |   "sentence": "['大', '码']",
1516 |   "labeled entities": "[]"
1517 |  },
1518 |  {
1519 |   "sentence": "['加', '菲', '猫', ' ', '婴', '儿', '沐', '浴', '露', '多', '少', '钱']",
1520 |   "labeled entities": "[(0, 2, 'pp'), (4, 8, 'cp')]"
1521 |  },
1522 |  {
1523 |   "sentence": "['我', '要', '买', '婴', '儿', '零', '食']",
1524 |   "labeled entities": "[(3, 6, 'cp')]"
1525 |  },
1526 |  {
1527 |   "sentence": "['我', '要', '买', '加', '热', '饭', '盒']",
1528 |   "labeled entities": "[(3, 6, 'cp')]"
1529 |  },
1530 |  {
1531 |   "sentence": "['半', '拖', '鞋']",
1532 |   "labeled entities": "[(1, 2, 'cp')]"
1533 |  },
1534 |  {
1535 |   "sentence": "['男', '士', '保', '湿', '多', '少', '钱']",
1536 |   "labeled entities": "[]"
1537 |  },
1538 |  {
1539 |   "sentence": "['新', '西', '兰', '苹', '果', '多', '少', '钱']",
1540 |   "labeled entities": "[(3, 4, 'cp')]"
1541 |  },
1542 |  {
1543 |   "sentence": "['我', '要', '买', '牙', '签']",
1544 |   "labeled entities": "[(3, 4, 'cp')]"
1545 |  },
1546 |  {
1547 |   "sentence": "['我', '要', '买', '干', '粮', '零', '食']",
1548 |   "labeled entities": "[(3, 4, 'cp'), (5, 6, 'cp')]"
1549 |  },
1550 |  {
1551 |   "sentence": "['蛋', '黄', '酥', '多', '少', '钱']",
1552 |   "labeled entities": "[(0, 2, 'cp')]"
1553 |  },
1554 |  {
1555 |   "sentence": "['我', '要', '买', '果', '干', '类']",
1556 |   "labeled entities": "[(3, 4, 'cp')]"
1557 |  },
1558 |  {
1559 |   "sentence": "['手', '撕', '面', '包', '整', '箱', '多', '少', '钱']",
1560 |   "labeled entities": "[(0, 3, 'cp'), (4, 5, 'gg')]"
1561 |  },
1562 |  {
1563 |   "sentence": "['无', '芯', '卷', '筒', '纸', '家', '用', '卫', '生', '纸', '多', '少', '钱']",
1564 |   "labeled entities": "[(0, 4, 'cp'), (5, 9, 'cp')]"
1565 |  },
1566 |  {
1567 |   "sentence": "['我', '要', '买', '鞋', '子', '收', '纳', '包']",
1568 |   "labeled entities": "[(3, 7, 'cp')]"
1569 |  },
1570 |  {
1571 |   "sentence": "['骁', '龙', '8', '2', '0']",
1572 |   "labeled entities": "[(0, 1, 'pp'), (2, 4, 'xh')]"
1573 |  },
1574 |  {
1575 |   "sentence": "['我', '要', '买', '竹', '签']",
1576 |   "labeled entities": "[(3, 4, 'cp')]"
1577 |  },
1578 |  {
1579 |   "sentence": "['辣', '酱', ' ', '拌', '饭', '酱', '多', '少', '钱']",
1580 |   "labeled entities": "[(0, 1, 'cp'), (3, 5, 'cp')]"
1581 |  },
1582 |  {
1583 |   "sentence": "['我', '要', '买', '胡', '豆']",
1584 |   "labeled entities": "[(3, 4, 'cp')]"
1585 |  },
1586 |  {
1587 |   "sentence": "['我', '要', '买', '三', '只', '松', '鼠', '爆', '米', '花']",
1588 |   "labeled entities": "[(3, 6, 'pp'), (7, 9, 'cp')]"
1589 |  },
1590 |  {
1591 |   "sentence": "['保', '鲜', '碗', '多', '少', '钱']",
1592 |   "labeled entities": "[(0, 2, 'cp')]"
1593 |  },
1594 |  {
1595 |   "sentence": "['我', '要', '买', '话', '梅', '棒', '棒', '糖']",
1596 |   "labeled entities": "[(3, 7, 'cp')]"
1597 |  },
1598 |  {
1599 |   "sentence": "['补', '钙', '多', '少', '钱']",
1600 |   "labeled entities": "[]"
1601 |  }
1602 | ]


--------------------------------------------------------------------------------
/dataset/EC/test.json:
--------------------------------------------------------------------------------
   1 | [
   2 |  {
   3 |   "sentence": "['梅', '干']",
   4 |   "labeled entities": "[(0, 1, 'cp')]"
   5 |  },
   6 |  {
   7 |   "sentence": "['我', '要', '买', '婴', '儿', '潮', '款', '衣', '服']",
   8 |   "labeled entities": "[(7, 8, 'cp')]"
   9 |  },
  10 |  {
  11 |   "sentence": "['宝', '宝', '可', '以', '开', '的', '挖', '机']",
  12 |   "labeled entities": "[(6, 7, 'cp')]"
  13 |  },
  14 |  {
  15 |   "sentence": "['有', '没', '有', '2', '5', '0', 'L', '的']",
  16 |   "labeled entities": "[(3, 6, 'gg')]"
  17 |  },
  18 |  {
  19 |   "sentence": "['有', '没', '有', '蒸', '面', '包', '呀']",
  20 |   "labeled entities": "[(3, 5, 'cp')]"
  21 |  },
  22 |  {
  23 |   "sentence": "['五', '菱', '宏', '光', 'S', '七', '座']",
  24 |   "labeled entities": "[(0, 1, 'pp'), (2, 4, 'xh'), (5, 6, 'gg')]"
  25 |  },
  26 |  {
  27 |   "sentence": "['信', '号', '强']",
  28 |   "labeled entities": "[]"
  29 |  },
  30 |  {
  31 |   "sentence": "['健', '身', '服', '夏', '装', '女']",
  32 |   "labeled entities": "[(0, 2, 'cp')]"
  33 |  },
  34 |  {
  35 |   "sentence": "['你', '们', '这', '个', '有', '人', '工', '服', '务', '，', '没', '有']",
  36 |   "labeled entities": "[]"
  37 |  },
  38 |  {
  39 |   "sentence": "['想', '买', '婴', '儿', '学', '饮', '杯']",
  40 |   "labeled entities": "[(4, 6, 'cp')]"
  41 |  },
  42 |  {
  43 |   "sentence": "['\\x08', 'u', '盘']",
  44 |   "labeled entities": "[(1, 2, 'cp')]"
  45 |  },
  46 |  {
  47 |   "sentence": "['胖', 'M', 'M', '上', '衣']",
  48 |   "labeled entities": "[(3, 4, 'cp')]"
  49 |  },
  50 |  {
  51 |   "sentence": "['为', '什', '么', '我', '想', '买', '票']",
  52 |   "labeled entities": "[]"
  53 |  },
  54 |  {
  55 |   "sentence": "['电', '动', '增', '压', '泵']",
  56 |   "labeled entities": "[(2, 4, 'cp')]"
  57 |  },
  58 |  {
  59 |   "sentence": "['挎', '短', '裤']",
  60 |   "labeled entities": "[(0, 2, 'cp')]"
  61 |  },
  62 |  {
  63 |   "sentence": "['我', '要', '买', '女', '童', '套', '装']",
  64 |   "labeled entities": "[(5, 6, 'cp')]"
  65 |  },
  66 |  {
  67 |   "sentence": "['周', '大', '福']",
  68 |   "labeled entities": "[(0, 2, 'pp')]"
  69 |  },
  70 |  {
  71 |   "sentence": "['地', '面', '积', '模']",
  72 |   "labeled entities": "[]"
  73 |  },
  74 |  {
  75 |   "sentence": "['带', '帽', '子']",
  76 |   "labeled entities": "[(1, 2, 'cp')]"
  77 |  },
  78 |  {
  79 |   "sentence": "['脱', '水', '洗', '衣', '机']",
  80 |   "labeled entities": "[(2, 4, 'cp')]"
  81 |  },
  82 |  {
  83 |   "sentence": "['我', '要', '买', '夏', '季', '韩', '版', '上', '衣', '女', '装']",
  84 |   "labeled entities": "[(7, 8, 'cp'), (9, 10, 'cp')]"
  85 |  },
  86 |  {
  87 |   "sentence": "['补', '水', '，', '美', '白', '，', '祛', '斑']",
  88 |   "labeled entities": "[]"
  89 |  },
  90 |  {
  91 |   "sentence": "['我', '想', '买', '笔', '可', '以', '不', '用', '红', '包', '吗', '优', '惠', '券', '刚', '好', '2', '1', '9']",
  92 |   "labeled entities": "[(3, 3, 'cp')]"
  93 |  },
  94 |  {
  95 |   "sentence": "['辣', '鸡', '辣', '鸡']",
  96 |   "labeled entities": "[]"
  97 |  },
  98 |  {
  99 |   "sentence": "['锹']",
 100 |   "labeled entities": "[(0, 0, 'cp')]"
 101 |  },
 102 |  {
 103 |   "sentence": "['爬', '行', '毯']",
 104 |   "labeled entities": "[(0, 2, 'cp')]"
 105 |  },
 106 |  {
 107 |   "sentence": "['情', '侣', '衬', '衫']",
 108 |   "labeled entities": "[(2, 3, 'cp')]"
 109 |  },
 110 |  {
 111 |   "sentence": "['手', '表', '式', '听', '歌', '用', '的']",
 112 |   "labeled entities": "[(0, 1, 'cp')]"
 113 |  },
 114 |  {
 115 |   "sentence": "['男', '式', '大', '破', '洞', '裤']",
 116 |   "labeled entities": "[(3, 5, 'cp')]"
 117 |  },
 118 |  {
 119 |   "sentence": "['买', '什', '么', '多', '肉', '植', '物', '最', '好', '？']",
 120 |   "labeled entities": "[(3, 6, 'cp')]"
 121 |  },
 122 |  {
 123 |   "sentence": "['我', '想', '要', '一', '个', '一', '米', '八', '的', '大', '熊', '，', '要', '可', '爱', '一', '点', '的', '漂', '亮', '一', '点', '的']",
 124 |   "labeled entities": "[]"
 125 |  },
 126 |  {
 127 |   "sentence": "['双', '头', '卧', '蚕', '笔']",
 128 |   "labeled entities": "[(0, 4, 'cp')]"
 129 |  },
 130 |  {
 131 |   "sentence": "['家', '用', '餐', '桌']",
 132 |   "labeled entities": "[(2, 3, 'cp')]"
 133 |  },
 134 |  {
 135 |   "sentence": "['休', '闲', '厅']",
 136 |   "labeled entities": "[]"
 137 |  },
 138 |  {
 139 |   "sentence": "['软', '底', '内', '增', '好', '的', '白', '鞋']",
 140 |   "labeled entities": "[(7, 7, 'cp')]"
 141 |  },
 142 |  {
 143 |   "sentence": "['o', 'p', 'p', 'o', 'r', '9', '个', '性', '手', '机', '壳']",
 144 |   "labeled entities": "[(0, 3, 'pp'), (4, 5, 'xh'), (8, 10, 'cp')]"
 145 |  },
 146 |  {
 147 |   "sentence": "['女', '学', '生', '板', '鞋']",
 148 |   "labeled entities": "[(3, 4, 'cp')]"
 149 |  },
 150 |  {
 151 |   "sentence": "['我', '想', '买', '辆', '自', '行', '车']",
 152 |   "labeled entities": "[(4, 6, 'cp')]"
 153 |  },
 154 |  {
 155 |   "sentence": "['我', '要', '买', '女', '春', '秋', '季', '学', '生', '连', '体', '睡', '衣']",
 156 |   "labeled entities": "[(11, 12, 'cp')]"
 157 |  },
 158 |  {
 159 |   "sentence": "['我', '要', '买', '春', '季', '的', '女', '士', '，', '续', '了', '平', '底', '儿', '鞋']",
 160 |   "labeled entities": "[(14, 14, 'cp')]"
 161 |  },
 162 |  {
 163 |   "sentence": "['亲', '，', '我', '刚', '买', '的', '花', '把', '地', '址', '和', '我', '写', '反', '了']",
 164 |   "labeled entities": "[(6, 6, 'cp')]"
 165 |  },
 166 |  {
 167 |   "sentence": "['碧', '罗', '春']",
 168 |   "labeled entities": "[(0, 2, 'cp')]"
 169 |  },
 170 |  {
 171 |   "sentence": "['运', '动', '鞋', '子', '1', '7', '岁', '女']",
 172 |   "labeled entities": "[(0, 2, 'cp')]"
 173 |  },
 174 |  {
 175 |   "sentence": "['购', '物', '卷', '可', '不', '可', '以', '叠', '加', '使', '用']",
 176 |   "labeled entities": "[]"
 177 |  },
 178 |  {
 179 |   "sentence": "['坚', '果', '混', '合']",
 180 |   "labeled entities": "[(0, 1, 'cp')]"
 181 |  },
 182 |  {
 183 |   "sentence": "['我', '说', '的', '意', '思', '是', '，', '我', '买', '个', '的', '东', '西', '都', '是', '还', '是', '显', '示', '在', '手', '机', '上', '面', '。']",
 184 |   "labeled entities": "[]"
 185 |  },
 186 |  {
 187 |   "sentence": "['长', '袖', '厚', '体', '恤']",
 188 |   "labeled entities": "[(3, 4, 'cp')]"
 189 |  },
 190 |  {
 191 |   "sentence": "['给', '闺', '密', '买', '生', '日', '礼', '物']",
 192 |   "labeled entities": "[]"
 193 |  },
 194 |  {
 195 |   "sentence": "['帮', '我', '推', '荐', '婴', '儿', '毛', '线', '帽', '子']",
 196 |   "labeled entities": "[(8, 9, 'cp')]"
 197 |  },
 198 |  {
 199 |   "sentence": "['办', '公', '设', '计', '的', '书', '籍']",
 200 |   "labeled entities": "[(5, 6, 'cp')]"
 201 |  },
 202 |  {
 203 |   "sentence": "['魅', '蓝', 'm', '2', '手', '机', '壳']",
 204 |   "labeled entities": "[(0, 1, 'pp'), (2, 3, 'xh'), (4, 6, 'cp')]"
 205 |  },
 206 |  {
 207 |   "sentence": "['好', '用', '的', '国', '货', '护', '肤', '品']",
 208 |   "labeled entities": "[(5, 7, 'cp')]"
 209 |  },
 210 |  {
 211 |   "sentence": "['道', '士', '小', '一', '点', '的']",
 212 |   "labeled entities": "[]"
 213 |  },
 214 |  {
 215 |   "sentence": "['小', '帆', '布', '包', '斜', '挎']",
 216 |   "labeled entities": "[(1, 3, 'cp')]"
 217 |  },
 218 |  {
 219 |   "sentence": "['我', '要', '买', '儿', '童', '车', '。', '可', '推', '可', '踩', '的', '三', '轮', '车']",
 220 |   "labeled entities": "[(3, 5, 'cp'), (12, 14, 'cp')]"
 221 |  },
 222 |  {
 223 |   "sentence": "['爬', '山', '工', '具']",
 224 |   "labeled entities": "[(0, 3, 'cp')]"
 225 |  },
 226 |  {
 227 |   "sentence": "['黄', '金', '吊', '坠']",
 228 |   "labeled entities": "[(0, 1, 'yl'), (2, 3, 'cp')]"
 229 |  },
 230 |  {
 231 |   "sentence": "['购', '物', '卷', '不', '能', '满', '减']",
 232 |   "labeled entities": "[]"
 233 |  },
 234 |  {
 235 |   "sentence": "['我', '想', '看', '看', '我', '的', '评', '价', '是', '什', '么', '，', '还', '有', '接', '头', '吗', '，', '还', '有', '那', '个', '图', '吗', '？']",
 236 |   "labeled entities": "[]"
 237 |  },
 238 |  {
 239 |   "sentence": "['有', '没', '有', '卖', '千', '里', '追', '风', '油', '的']",
 240 |   "labeled entities": "[(4, 8, 'cp')]"
 241 |  },
 242 |  {
 243 |   "sentence": "['太', '小', '气', '了']",
 244 |   "labeled entities": "[]"
 245 |  },
 246 |  {
 247 |   "sentence": "['我', '想', '买', '诺', '和', '笔', '5', '的', '针', '头']",
 248 |   "labeled entities": "[(3, 5, 'cp'), (6, 6, 'xh'), (8, 9, 'cp')]"
 249 |  },
 250 |  {
 251 |   "sentence": "['粥', '，', '可', '以', '自', '己', '煮', '的']",
 252 |   "labeled entities": "[(0, 0, 'cp')]"
 253 |  },
 254 |  {
 255 |   "sentence": "['我', '要', '华', '为', '荣', '耀', 'v', '9']",
 256 |   "labeled entities": "[(2, 3, 'pp'), (4, 5, 'pp'), (6, 7, 'xh')]"
 257 |  },
 258 |  {
 259 |   "sentence": "['最', '好', '是', '发', '饰', '之', '类', '的']",
 260 |   "labeled entities": "[(3, 4, 'cp')]"
 261 |  },
 262 |  {
 263 |   "sentence": "['买', '杯', '子']",
 264 |   "labeled entities": "[(1, 2, 'cp')]"
 265 |  },
 266 |  {
 267 |   "sentence": "['买', '苹', '果', 's', 'e', '手', '机']",
 268 |   "labeled entities": "[(1, 2, 'pp'), (3, 4, 'xh'), (5, 6, 'cp')]"
 269 |  },
 270 |  {
 271 |   "sentence": "['软', '皮', '包', '包']",
 272 |   "labeled entities": "[(2, 3, 'cp')]"
 273 |  },
 274 |  {
 275 |   "sentence": "['泡', '酒']",
 276 |   "labeled entities": "[(0, 1, 'cp')]"
 277 |  },
 278 |  {
 279 |   "sentence": "['买', '芒', '果']",
 280 |   "labeled entities": "[(1, 2, 'cp')]"
 281 |  },
 282 |  {
 283 |   "sentence": "['我', '要', '性', '价', '比', '高', '的', '耳', '机']",
 284 |   "labeled entities": "[(7, 8, 'cp')]"
 285 |  },
 286 |  {
 287 |   "sentence": "['老', '婆', '1', '5', '0', '斤', '，', '请', '问', '买', '什', '么', '形', '号', '的', '内', '裤', '？']",
 288 |   "labeled entities": "[(15, 16, 'cp')]"
 289 |  },
 290 |  {
 291 |   "sentence": "['买', '牛', '肉', '丝']",
 292 |   "labeled entities": "[(1, 3, 'cp')]"
 293 |  },
 294 |  {
 295 |   "sentence": "['我', '要', '买', '收', '腰', '长', '袖', '衫', '学', '生', '女']",
 296 |   "labeled entities": "[(5, 7, 'cp')]"
 297 |  },
 298 |  {
 299 |   "sentence": "['护', '肤', '水', '单', '件']",
 300 |   "labeled entities": "[(0, 2, 'cp')]"
 301 |  },
 302 |  {
 303 |   "sentence": "['超', '轻']",
 304 |   "labeled entities": "[]"
 305 |  },
 306 |  {
 307 |   "sentence": "['助', '性', '工', '具']",
 308 |   "labeled entities": "[]"
 309 |  },
 310 |  {
 311 |   "sentence": "['美', '白', '保', '湿', '美', '白', '去', '斑', '去', '黄', '用', '，', '却', '是']",
 312 |   "labeled entities": "[]"
 313 |  },
 314 |  {
 315 |   "sentence": "['金', '骏', '眉', '与', '正', '山', '小', '种', '有', '什', '么', '区', '别', '？']",
 316 |   "labeled entities": "[(0, 2, 'cp'), (4, 7, 'cp')]"
 317 |  },
 318 |  {
 319 |   "sentence": "['请', '问', '1', '岁', '小', '孩', '买', '什', '么', '玩', '具']",
 320 |   "labeled entities": "[(9, 10, 'cp')]"
 321 |  },
 322 |  {
 323 |   "sentence": "['5', '0', '左', '右']",
 324 |   "labeled entities": "[]"
 325 |  },
 326 |  {
 327 |   "sentence": "['有', '没', '有', '又', '便', '宜', '又', '是', '一', '身', '的', '工', '作', '服']",
 328 |   "labeled entities": "[(11, 13, 'cp')]"
 329 |  },
 330 |  {
 331 |   "sentence": "['2', '4', '岁', '身', '高', '1', '7', '6', '体', '重', '1', '7', '0', '想', '买', '衣', '服']",
 332 |   "labeled entities": "[(15, 16, 'cp')]"
 333 |  },
 334 |  {
 335 |   "sentence": "['炫', '迈']",
 336 |   "labeled entities": "[(0, 1, 'pp')]"
 337 |  },
 338 |  {
 339 |   "sentence": "['我', '想', '找', '儿', '童', '自', '行', '车']",
 340 |   "labeled entities": "[(3, 7, 'cp')]"
 341 |  },
 342 |  {
 343 |   "sentence": "['我', '要', '买', '电', '动', '遥', '控', '四', '轮', '车', '钥', '匙', '启', '动']",
 344 |   "labeled entities": "[(7, 9, 'cp')]"
 345 |  },
 346 |  {
 347 |   "sentence": "['真', '皮', '浅', '口', '单', '鞋', '女']",
 348 |   "labeled entities": "[(0, 1, 'yl'), (2, 5, 'cp')]"
 349 |  },
 350 |  {
 351 |   "sentence": "['3', '6', '0', 'N', '5', '手', '机', '1', '3', '9', '9', '元', '可', '以', '买', '到', '吗', '？']",
 352 |   "labeled entities": "[(0, 2, 'pp'), (3, 4, 'xh'), (5, 6, 'cp')]"
 353 |  },
 354 |  {
 355 |   "sentence": "['修', '身', '显', '瘦']",
 356 |   "labeled entities": "[]"
 357 |  },
 358 |  {
 359 |   "sentence": "['宝', '格', '丽']",
 360 |   "labeled entities": "[(0, 2, 'pp')]"
 361 |  },
 362 |  {
 363 |   "sentence": "['这', '个', '太', '便', '宜', '了', '，', '黏', '胶', '货']",
 364 |   "labeled entities": "[]"
 365 |  },
 366 |  {
 367 |   "sentence": "['我', '要', '买', '护', '手', '霜']",
 368 |   "labeled entities": "[(3, 5, 'cp')]"
 369 |  },
 370 |  {
 371 |   "sentence": "['女', ' ', '上', '衣', '下', '衣', '都', '可', '以']",
 372 |   "labeled entities": "[(2, 3, 'cp'), (4, 5, 'cp')]"
 373 |  },
 374 |  {
 375 |   "sentence": "['2', '8', '4', '2', '6', '5', '2']",
 376 |   "labeled entities": "[]"
 377 |  },
 378 |  {
 379 |   "sentence": "['玩', '具', '毕', '业', '炮']",
 380 |   "labeled entities": "[(2, 4, 'cp')]"
 381 |  },
 382 |  {
 383 |   "sentence": "['想', '买', '耳', '机', '子']",
 384 |   "labeled entities": "[(2, 3, 'cp')]"
 385 |  },
 386 |  {
 387 |   "sentence": "['我', '要', '买', '拉', '拉', '裤']",
 388 |   "labeled entities": "[(3, 5, 'cp')]"
 389 |  },
 390 |  {
 391 |   "sentence": "['想', '买', '套', '护', '肤', '品']",
 392 |   "labeled entities": "[(3, 5, 'cp')]"
 393 |  },
 394 |  {
 395 |   "sentence": "['我', '要', '买', '炖', '盅']",
 396 |   "labeled entities": "[(3, 4, 'cp')]"
 397 |  },
 398 |  {
 399 |   "sentence": "['婴', '儿', '三', '轮', '推', '车']",
 400 |   "labeled entities": "[(2, 5, 'cp')]"
 401 |  },
 402 |  {
 403 |   "sentence": "['修', '身', '马', '甲']",
 404 |   "labeled entities": "[(2, 3, 'cp')]"
 405 |  },
 406 |  {
 407 |   "sentence": "['淡', '香']",
 408 |   "labeled entities": "[]"
 409 |  },
 410 |  {
 411 |   "sentence": "['你', '给', '我', '推', '荐', '这', '样', '的', '茶', '叶', '，', '你', '这', '么', '有', '本', '事', '咋', '不', '上', '天', '呢']",
 412 |   "labeled entities": "[(8, 9, 'cp')]"
 413 |  },
 414 |  {
 415 |   "sentence": "['有', '没', '有', '好', '的', '宝', '贝', '可', '以', '推', '荐']",
 416 |   "labeled entities": "[]"
 417 |  },
 418 |  {
 419 |   "sentence": "['算', '了', '，', '辛', '苦', '小', '蜜', '了']",
 420 |   "labeled entities": "[]"
 421 |  },
 422 |  {
 423 |   "sentence": "['春', '款', '衣', '服', '女']",
 424 |   "labeled entities": "[(2, 3, 'cp')]"
 425 |  },
 426 |  {
 427 |   "sentence": "['上', '火', '，', '买', '什', '么', '药', '效', '果', '好']",
 428 |   "labeled entities": "[(6, 6, 'cp')]"
 429 |  },
 430 |  {
 431 |   "sentence": "['我', '想', '买', '东', '西', '，', '提', '示', '买', '家', '账', '号', '错', '误']",
 432 |   "labeled entities": "[]"
 433 |  },
 434 |  {
 435 |   "sentence": "['鲁', '花', '菜', '籽', '油']",
 436 |   "labeled entities": "[(0, 1, 'pp'), (2, 4, 'cp')]"
 437 |  },
 438 |  {
 439 |   "sentence": "['短', '裤', '男']",
 440 |   "labeled entities": "[(0, 1, 'cp')]"
 441 |  },
 442 |  {
 443 |   "sentence": "['适', '合', '山', '东', '春', '天', '穿', '的', '孕', '妇', '套', '装']",
 444 |   "labeled entities": "[(8, 11, 'cp')]"
 445 |  },
 446 |  {
 447 |   "sentence": "['橡', '皮', '糖']",
 448 |   "labeled entities": "[(0, 2, 'cp')]"
 449 |  },
 450 |  {
 451 |   "sentence": "['马', '尾', '假', '发', ' ', '中', '长']",
 452 |   "labeled entities": "[(2, 3, 'cp')]"
 453 |  },
 454 |  {
 455 |   "sentence": "['高', '效', '化', '妆', '水']",
 456 |   "labeled entities": "[(2, 4, 'cp')]"
 457 |  },
 458 |  {
 459 |   "sentence": "['买', '东', '西', '商', '家', '让', '我', '推', '荐', '，', '有', '证', '据', '，', '如', '何', '投', '诉']",
 460 |   "labeled entities": "[]"
 461 |  },
 462 |  {
 463 |   "sentence": "['乐', '视', '手', '机', '质', '量', '好', '不', '好', '？']",
 464 |   "labeled entities": "[(0, 1, 'pp'), (2, 3, 'cp')]"
 465 |  },
 466 |  {
 467 |   "sentence": "['我', '要', '买', '白', '色', '卫', '衣']",
 468 |   "labeled entities": "[(5, 6, 'cp')]"
 469 |  },
 470 |  {
 471 |   "sentence": "['纹', '身', '膏']",
 472 |   "labeled entities": "[(0, 2, 'cp')]"
 473 |  },
 474 |  {
 475 |   "sentence": "['一', '品', '望', '家']",
 476 |   "labeled entities": "[(0, 3, 'pp')]"
 477 |  },
 478 |  {
 479 |   "sentence": "['春', '季', '新', '款', '女', '装', '上', '衣', '，', '连', '衣', '裙']",
 480 |   "labeled entities": "[(4, 5, 'cp'), (6, 7, 'cp'), (9, 11, 'cp')]"
 481 |  },
 482 |  {
 483 |   "sentence": "['您', '好', '，', '我', '想', '买', '右', '佐', '匹', '克', '隆', '片', '，', '有', '卖', '的', '吗', '？']",
 484 |   "labeled entities": "[(6, 11, 'cp')]"
 485 |  },
 486 |  {
 487 |   "sentence": "['小', '蜜', '，', '问', '你', '个', '事']",
 488 |   "labeled entities": "[]"
 489 |  },
 490 |  {
 491 |   "sentence": "['我', '想', '下', '载', '大', '码', '美', '衣']",
 492 |   "labeled entities": "[]"
 493 |  },
 494 |  {
 495 |   "sentence": "['嫁', '接', '睫', '毛', '9', 'D']",
 496 |   "labeled entities": "[(0, 3, 'cp'), (4, 5, 'xh')]"
 497 |  },
 498 |  {
 499 |   "sentence": "['男', '士', '九', '分', '裤']",
 500 |   "labeled entities": "[(2, 4, 'cp')]"
 501 |  },
 502 |  {
 503 |   "sentence": "['大', '码', '吊', '带', '长', '裙']",
 504 |   "labeled entities": "[(2, 5, 'cp')]"
 505 |  },
 506 |  {
 507 |   "sentence": "['我', '要', '吃', '坚', '果']",
 508 |   "labeled entities": "[(3, 4, 'cp')]"
 509 |  },
 510 |  {
 511 |   "sentence": "['我', '想', '买', '护', '腰', '带']",
 512 |   "labeled entities": "[(3, 5, 'cp')]"
 513 |  },
 514 |  {
 515 |   "sentence": "['我', '要', '找', '欧', '美', '风', '格', '女', '装']",
 516 |   "labeled entities": "[(7, 8, 'cp')]"
 517 |  },
 518 |  {
 519 |   "sentence": "['有', '没', '有', '便', '宜', '的', '手', '机', '？']",
 520 |   "labeled entities": "[(6, 7, 'cp')]"
 521 |  },
 522 |  {
 523 |   "sentence": "['求', '推', '荐', '1', 'T', '硬', '盘']",
 524 |   "labeled entities": "[(3, 4, 'gg'), (5, 6, 'cp')]"
 525 |  },
 526 |  {
 527 |   "sentence": "['想', '买', '性', '用', '品']",
 528 |   "labeled entities": "[(2, 4, 'cp')]"
 529 |  },
 530 |  {
 531 |   "sentence": "['我', '要', '找', '情', '趣', '内', '衣', '，', '性', '感', '一', '点', '的', '呦']",
 532 |   "labeled entities": "[(3, 6, 'cp')]"
 533 |  },
 534 |  {
 535 |   "sentence": "['我', '要', '买', '蓝', '牙', '游', '戏', '手', '柄']",
 536 |   "labeled entities": "[(5, 8, 'cp')]"
 537 |  },
 538 |  {
 539 |   "sentence": "['3', '1', '女', '人', '的', '衣', '服']",
 540 |   "labeled entities": "[(5, 6, 'cp')]"
 541 |  },
 542 |  {
 543 |   "sentence": "['嫂', '子', '是', '微', '博', '，', '康', '，', '是', '七', '十', '八', '不', '多', '的', '时', '候', '嘞']",
 544 |   "labeled entities": "[]"
 545 |  },
 546 |  {
 547 |   "sentence": "['润', '肤', '的']",
 548 |   "labeled entities": "[]"
 549 |  },
 550 |  {
 551 |   "sentence": "['不', '好', '意', '思', '是', '个', '小', '女', '生', '儿', '，', '我', '想', '要', '一', '个', '可', '爱', '漂', '亮', '的', '耳', '环', '，', '而', '且', '是', '而', '且', '是', '小', '女', '生', '，', '学', '生', '戴', '的', '耳', '环', '。']",
 552 |   "labeled entities": "[(21, 22, 'cp'), (38, 39, 'cp')]"
 553 |  },
 554 |  {
 555 |   "sentence": "['5', '0', '0', '0', '0', '充', '电', '宝']",
 556 |   "labeled entities": "[(0, 4, 'gg'), (5, 7, 'cp')]"
 557 |  },
 558 |  {
 559 |   "sentence": "['汽', '车', '发', '动', '机']",
 560 |   "labeled entities": "[(0, 4, 'cp')]"
 561 |  },
 562 |  {
 563 |   "sentence": "['我', '要', '买', '性', '能', '高', '的', '游', '戏', '本']",
 564 |   "labeled entities": "[(7, 9, 'cp')]"
 565 |  },
 566 |  {
 567 |   "sentence": "['华', '为', '手', '机', '和', '荣', '耀', '的', '区', '别']",
 568 |   "labeled entities": "[(0, 1, 'pp'), (2, 3, 'cp'), (5, 6, 'pp')]"
 569 |  },
 570 |  {
 571 |   "sentence": "['推', '荐', '女', '鞋', '店', '铺', '.', '有', '4', '0', '码', '女', '鞋', '就', '行']",
 572 |   "labeled entities": "[(2, 3, 'cp'), (8, 10, 'gg'), (11, 12, 'cp')]"
 573 |  },
 574 |  {
 575 |   "sentence": "['想', '买', '只', '保', '温', '壸', '盖', '子']",
 576 |   "labeled entities": "[(3, 7, 'cp')]"
 577 |  },
 578 |  {
 579 |   "sentence": "['可', '以', '其', '他', '类', '型', '的', '吗']",
 580 |   "labeled entities": "[]"
 581 |  },
 582 |  {
 583 |   "sentence": "['有', '没', '有', '能', '放', '下', '驾', '驶', '证', '的', '短', '款', '钱', '包']",
 584 |   "labeled entities": "[(12, 13, 'cp')]"
 585 |  },
 586 |  {
 587 |   "sentence": "['搭', '配', '绿', '色', '连', '衣', '裙', '裤', '的', '鞋', '子']",
 588 |   "labeled entities": "[(4, 7, 'cp'), (9, 10, 'cp')]"
 589 |  },
 590 |  {
 591 |   "sentence": "['我', '想', '买', '女', '包', '斜', '挎', '包', '小', '包']",
 592 |   "labeled entities": "[(3, 4, 'cp'), (5, 7, 'cp'), (9, 9, 'cp')]"
 593 |  },
 594 |  {
 595 |   "sentence": "['草', '莓', '发', '卡']",
 596 |   "labeled entities": "[(2, 3, 'cp')]"
 597 |  },
 598 |  {
 599 |   "sentence": "['購', '物', '卷', '怎', '麼', '使', '用']",
 600 |   "labeled entities": "[]"
 601 |  },
 602 |  {
 603 |   "sentence": "['我', '有', '黑', '头', '，', '毛', '孔', '粗', '大', '，', '还', '有', '痘', '印', '，', '你', '帮', '我', '推', '荐', '几', '款']",
 604 |   "labeled entities": "[]"
 605 |  },
 606 |  {
 607 |   "sentence": "['小', '孩', '子', '三', '轮', '子']",
 608 |   "labeled entities": "[(3, 5, 'cp')]"
 609 |  },
 610 |  {
 611 |   "sentence": "['我', '想', '买', '纸', '尿', '裤', '可', '么', '都', '没', '大', '小', '码', '可', '挑', '呢']",
 612 |   "labeled entities": "[(3, 5, 'cp')]"
 613 |  },
 614 |  {
 615 |   "sentence": "['买', '那', '个', '门', '铃', '帮', '我', '开', '发', '票']",
 616 |   "labeled entities": "[(3, 4, 'cp')]"
 617 |  },
 618 |  {
 619 |   "sentence": "['我', '要', '买', '东', '西', '，', '客', '服', '没', '有', '回', '应']",
 620 |   "labeled entities": "[]"
 621 |  },
 622 |  {
 623 |   "sentence": "['唱', '戏', '机']",
 624 |   "labeled entities": "[(0, 2, 'cp')]"
 625 |  },
 626 |  {
 627 |   "sentence": "['野', '钓', '饲', '料']",
 628 |   "labeled entities": "[(2, 3, 'cp')]"
 629 |  },
 630 |  {
 631 |   "sentence": "['粉', '铺']",
 632 |   "labeled entities": "[(0, 1, 'cp')]"
 633 |  },
 634 |  {
 635 |   "sentence": "['我', '想', '买', '个', '商', '品', '在', '哪', '里', '拍', '下', '来']",
 636 |   "labeled entities": "[]"
 637 |  },
 638 |  {
 639 |   "sentence": "['粘', '土', '模', '具', '应', '该', '买', '什', '么', '好', '？']",
 640 |   "labeled entities": "[(2, 3, 'cp')]"
 641 |  },
 642 |  {
 643 |   "sentence": "['买', '衣', '服', '没', '有', '钱', '可', '不', '可', '以', '抵', '账']",
 644 |   "labeled entities": "[(1, 2, 'cp')]"
 645 |  },
 646 |  {
 647 |   "sentence": "['半', '球']",
 648 |   "labeled entities": "[]"
 649 |  },
 650 |  {
 651 |   "sentence": "['美', '白', '，', '去', '斑', '。']",
 652 |   "labeled entities": "[]"
 653 |  },
 654 |  {
 655 |   "sentence": "['灯', '灯', '灯']",
 656 |   "labeled entities": "[(0, 0, 'cp'), (1, 1, 'cp'), (2, 2, 'cp')]"
 657 |  },
 658 |  {
 659 |   "sentence": "['移', '动', '牌']",
 660 |   "labeled entities": "[(0, 2, 'pp')]"
 661 |  },
 662 |  {
 663 |   "sentence": "['计', '步', '器']",
 664 |   "labeled entities": "[(0, 2, 'cp')]"
 665 |  },
 666 |  {
 667 |   "sentence": "['我', '要', '买', '罗', '技', '游', '戏', '鼠', '标']",
 668 |   "labeled entities": "[(3, 4, 'pp'), (7, 8, 'cp')]"
 669 |  },
 670 |  {
 671 |   "sentence": "['哺', '乳', '期', '吃', '的', '零', '食']",
 672 |   "labeled entities": "[(5, 6, 'cp')]"
 673 |  },
 674 |  {
 675 |   "sentence": "['真', '皮', '鞋']",
 676 |   "labeled entities": "[(0, 1, 'yl'), (2, 2, 'cp')]"
 677 |  },
 678 |  {
 679 |   "sentence": "['我', '要', '定', '型', '保', '湿', '不', '油', '腻', '的', '头', '发', '喷', '雾']",
 680 |   "labeled entities": "[(12, 13, 'cp')]"
 681 |  },
 682 |  {
 683 |   "sentence": "['女', '士', '休', '闲', '鞋']",
 684 |   "labeled entities": "[(2, 4, 'cp')]"
 685 |  },
 686 |  {
 687 |   "sentence": "['想', '买', '薄', '的', '手', '机']",
 688 |   "labeled entities": "[(4, 5, 'cp')]"
 689 |  },
 690 |  {
 691 |   "sentence": "['翡', '翠', '玫', '瑰', '花']",
 692 |   "labeled entities": "[(0, 4, 'cp')]"
 693 |  },
 694 |  {
 695 |   "sentence": "['小', '孩', '体', '质', '差', '，', '我', '想', '买', '个', '免', '疫', '球', '蛋', '白', '给', '他', '吃', '，', '什', '么', '牌', '子', '的', '效', '果', '好', '些']",
 696 |   "labeled entities": "[(10, 14, 'cp')]"
 697 |  },
 698 |  {
 699 |   "sentence": "['东', '西', '太', '贵', '了']",
 700 |   "labeled entities": "[]"
 701 |  },
 702 |  {
 703 |   "sentence": "['青', '少', '年']",
 704 |   "labeled entities": "[]"
 705 |  },
 706 |  {
 707 |   "sentence": "['不', '要', '韩', '货']",
 708 |   "labeled entities": "[]"
 709 |  },
 710 |  {
 711 |   "sentence": "['吸', '黑', '头']",
 712 |   "labeled entities": "[]"
 713 |  },
 714 |  {
 715 |   "sentence": "['化', '妆', '刷']",
 716 |   "labeled entities": "[(0, 2, 'cp')]"
 717 |  },
 718 |  {
 719 |   "sentence": "['我', '要', '买', '唇', '液']",
 720 |   "labeled entities": "[(3, 4, 'cp')]"
 721 |  },
 722 |  {
 723 |   "sentence": "['美', '图', 'm', '6', 's']",
 724 |   "labeled entities": "[(0, 1, 'pp'), (2, 4, 'xh')]"
 725 |  },
 726 |  {
 727 |   "sentence": "['控', '油', '的', '呢']",
 728 |   "labeled entities": "[]"
 729 |  },
 730 |  {
 731 |   "sentence": "['我', '想', '买', '短', '的', '牛', '仔', '裤']",
 732 |   "labeled entities": "[(5, 7, 'cp')]"
 733 |  },
 734 |  {
 735 |   "sentence": "['白', '色', '连', '衣', '长', '裙']",
 736 |   "labeled entities": "[(4, 5, 'cp')]"
 737 |  },
 738 |  {
 739 |   "sentence": "['破', '洞', '牛', '仔', '牛', '仔', '裤']",
 740 |   "labeled entities": "[(4, 6, 'cp')]"
 741 |  },
 742 |  {
 743 |   "sentence": "['我', '要', '买', '多', '浆', '植', '物']",
 744 |   "labeled entities": "[(3, 6, 'cp')]"
 745 |  },
 746 |  {
 747 |   "sentence": "['汽', '车', '硅', '胶', '管']",
 748 |   "labeled entities": "[(0, 4, 'cp')]"
 749 |  },
 750 |  {
 751 |   "sentence": "['十', '字', '绣', '真', '实', '回', '收', '的']",
 752 |   "labeled entities": "[(0, 2, 'cp')]"
 753 |  },
 754 |  {
 755 |   "sentence": "['我', '要', '买', '青', '少', '年', '喝', '的', '羊', '奶', '请', '推', '荐']",
 756 |   "labeled entities": "[(8, 9, 'cp')]"
 757 |  },
 758 |  {
 759 |   "sentence": "['成', '语', '故', '事', '书']",
 760 |   "labeled entities": "[(2, 4, 'cp')]"
 761 |  },
 762 |  {
 763 |   "sentence": "['都', '太', '贵', '了', '能', '便', '宜', '一', '点', '的']",
 764 |   "labeled entities": "[]"
 765 |  },
 766 |  {
 767 |   "sentence": "['男', '士', '香', '体']",
 768 |   "labeled entities": "[(2, 3, 'cp')]"
 769 |  },
 770 |  {
 771 |   "sentence": "['我', '要', '买', '祛', '痘', '印']",
 772 |   "labeled entities": "[]"
 773 |  },
 774 |  {
 775 |   "sentence": "['背', '带', '裤', '1', '5', '-', '1', '6']",
 776 |   "labeled entities": "[(0, 2, 'cp')]"
 777 |  },
 778 |  {
 779 |   "sentence": "['您', '好', '，', '我', '拍', '错', '了', '，', '想', '要', '菲', '克', '斯', '曼', '家', '用', '工', '具', '箱', '1', '7', '寸', 'z', '0', '1', '0', '3']",
 780 |   "labeled entities": "[(10, 13, 'pp'), (16, 18, 'cp'), (19, 21, 'gg'), (22, 26, 'xh')]"
 781 |  },
 782 |  {
 783 |   "sentence": "['或', '妆', '品']",
 784 |   "labeled entities": "[(1, 2, 'cp')]"
 785 |  },
 786 |  {
 787 |   "sentence": "['小', '个', '的', '糖', '盒']",
 788 |   "labeled entities": "[(3, 4, 'cp')]"
 789 |  },
 790 |  {
 791 |   "sentence": "['我', '要', '买', '口', '红', '，', '豆', '沙', '色', ' ', '，', '雾', '面', '，', '大', '牌', '子']",
 792 |   "labeled entities": "[(3, 4, 'cp')]"
 793 |  },
 794 |  {
 795 |   "sentence": "['淘', '宝', '到', '底', '有', '没', '有', '人', '工', '客', '服', '？']",
 796 |   "labeled entities": "[]"
 797 |  },
 798 |  {
 799 |   "sentence": "['B', 'B', '霜', '和', '隔', '离', '霜', '组', '合']",
 800 |   "labeled entities": "[(0, 2, 'cp'), (4, 6, 'cp')]"
 801 |  },
 802 |  {
 803 |   "sentence": "['可', '可', '粉', '模', '具']",
 804 |   "labeled entities": "[(0, 4, 'cp')]"
 805 |  },
 806 |  {
 807 |   "sentence": "['笔', '记', '本', '4', 'G', '内', '存']",
 808 |   "labeled entities": "[(0, 2, 'cp'), (3, 4, 'gg')]"
 809 |  },
 810 |  {
 811 |   "sentence": "['我', '的', '奶', '奶', '生', '日', '要', '到', '了', '，', '可', '以', '给', '我', '推', '荐', '什', '么', '合', '适', '的', '生', '日', '礼', '物', '吗']",
 812 |   "labeled entities": "[]"
 813 |  },
 814 |  {
 815 |   "sentence": "['我', '要', '买', '普', '洱', '生', '茶']",
 816 |   "labeled entities": "[(3, 6, 'cp')]"
 817 |  },
 818 |  {
 819 |   "sentence": "['有', '没', '有', '什', '么', '辣', '条', '好', '吃', '的']",
 820 |   "labeled entities": "[(5, 6, 'cp')]"
 821 |  },
 822 |  {
 823 |   "sentence": "['购', '推', '荐', '个', '女', '款', '半', '截', '袖', '的', '连', '接', '，', '我', '看', '看']",
 824 |   "labeled entities": "[]"
 825 |  },
 826 |  {
 827 |   "sentence": "['电', '脑', '配', '件']",
 828 |   "labeled entities": "[(0, 3, 'cp')]"
 829 |  },
 830 |  {
 831 |   "sentence": "['男', '生', '七', '分', '裤']",
 832 |   "labeled entities": "[(2, 4, 'cp')]"
 833 |  },
 834 |  {
 835 |   "sentence": "['吹', '风', '机', '静', '音']",
 836 |   "labeled entities": "[(0, 2, 'cp')]"
 837 |  },
 838 |  {
 839 |   "sentence": "['1', '3', '9', '还', '一', '个', '裙', '子', '，', '你', '有', '没', '搞', '错', '，', '那', '么', '贵']",
 840 |   "labeled entities": "[(6, 7, 'cp')]"
 841 |  },
 842 |  {
 843 |   "sentence": "['带', '魔', '音', '手', '机']",
 844 |   "labeled entities": "[(3, 4, 'cp')]"
 845 |  },
 846 |  {
 847 |   "sentence": "['有', '没', '有', '去', '廊', '坊', '的', '火', '车']",
 848 |   "labeled entities": "[]"
 849 |  },
 850 |  {
 851 |   "sentence": "['有', '女', '票', '吗']",
 852 |   "labeled entities": "[]"
 853 |  },
 854 |  {
 855 |   "sentence": "['有', '卖', '安', '眠', '药', '吗']",
 856 |   "labeled entities": "[(2, 4, 'cp')]"
 857 |  },
 858 |  {
 859 |   "sentence": "['2', '0', '1', '7', '夏', '季', '女', '装']",
 860 |   "labeled entities": "[(6, 7, 'cp')]"
 861 |  },
 862 |  {
 863 |   "sentence": "['找', 'o', '-', '2', '0', '块', '钱', '的', '套', '装']",
 864 |   "labeled entities": "[(8, 9, 'cp')]"
 865 |  },
 866 |  {
 867 |   "sentence": "['休', '闲', '运', '动', '鞋', '百', '搭', '的']",
 868 |   "labeled entities": "[(2, 4, 'cp')]"
 869 |  },
 870 |  {
 871 |   "sentence": "['我', '要', '买', '内', '蒙', '古', '生', '产', '的', '神', '奇', '牌', '小', '活', '络', '丸']",
 872 |   "labeled entities": "[(9, 11, 'pp'), (12, 15, 'cp')]"
 873 |  },
 874 |  {
 875 |   "sentence": "['金', '币', '领', '到', '一', '百', '就', '领', '不', '了']",
 876 |   "labeled entities": "[]"
 877 |  },
 878 |  {
 879 |   "sentence": "['乳']",
 880 |   "labeled entities": "[]"
 881 |  },
 882 |  {
 883 |   "sentence": "['我', '要', '买', '烘', '干', '架']",
 884 |   "labeled entities": "[(3, 5, 'cp')]"
 885 |  },
 886 |  {
 887 |   "sentence": "['我', '想', '找', '洋', '葱', '圈']",
 888 |   "labeled entities": "[(3, 5, 'cp')]"
 889 |  },
 890 |  {
 891 |   "sentence": "['长', '城']",
 892 |   "labeled entities": "[(0, 1, 'pp')]"
 893 |  },
 894 |  {
 895 |   "sentence": "['我', '想', '要', '结', '婚', '婚', '纱', ' ', '又', '便', '宜', '又', '好', '看']",
 896 |   "labeled entities": "[(5, 6, 'cp')]"
 897 |  },
 898 |  {
 899 |   "sentence": "['碳', '烤']",
 900 |   "labeled entities": "[]"
 901 |  },
 902 |  {
 903 |   "sentence": "['便', '宜', '的', '乳', '液']",
 904 |   "labeled entities": "[(3, 4, 'cp')]"
 905 |  },
 906 |  {
 907 |   "sentence": "['想', '买', '汽', '车', '座', '套']",
 908 |   "labeled entities": "[(2, 5, 'cp')]"
 909 |  },
 910 |  {
 911 |   "sentence": "['夹', '克', '衫', '修', '身']",
 912 |   "labeled entities": "[(0, 2, 'cp')]"
 913 |  },
 914 |  {
 915 |   "sentence": "['我', '想', '买', '工', '作', '服', '装', '带', '执', '勤', '臂', '章', '的', '短', '袖', '衬', '衫']",
 916 |   "labeled entities": "[(3, 5, 'cp'), (13, 16, 'cp')]"
 917 |  },
 918 |  {
 919 |   "sentence": "['福', '利', '社', '小', '蜜']",
 920 |   "labeled entities": "[]"
 921 |  },
 922 |  {
 923 |   "sentence": "['送', '你', '什', '么', '花']",
 924 |   "labeled entities": "[(4, 4, 'cp')]"
 925 |  },
 926 |  {
 927 |   "sentence": "['夏', '季', '鞋', '子']",
 928 |   "labeled entities": "[(2, 3, 'cp')]"
 929 |  },
 930 |  {
 931 |   "sentence": "['白', '色', '外', '套', '配', '什', '么', '颜', '色']",
 932 |   "labeled entities": "[(2, 3, 'cp')]"
 933 |  },
 934 |  {
 935 |   "sentence": "['想', '买', '中', '老', '年', '男', '春', '秋', '薄', '款', '实', '棉', '睡', '衣', '裤', '子', '一', '百', '四', '十', '斤', '左', '右']",
 936 |   "labeled entities": "[(11, 11, 'yl'), (12, 13, 'cp'), (14, 15, 'cp')]"
 937 |  },
 938 |  {
 939 |   "sentence": "['女', '孩', '儿', '的', '，', '单', '肩', '背', '包']",
 940 |   "labeled entities": "[(5, 8, 'cp')]"
 941 |  },
 942 |  {
 943 |   "sentence": "['选', '移', '动', '电', '源', '？', '其', '实', '可', '以', '很', '简', '单', '！', ' ', '数', '码', '达', '人', 'o', 'r', '电', '器', '小', '白', '都', '不', '怕', '！', '快', '试', '试', '发', '送', '“', '我', '要', '买', '移', '动', '电', '源', '”', '或', '其', '他', '需', '求', '，', '让', '小', '蜜', '帮', '你', '挑', '吧', '~', ' ', '发', '送', '试', '试']",
 944 |   "labeled entities": "[(1, 4, 'cp'), (38, 41, 'cp')]"
 945 |  },
 946 |  {
 947 |   "sentence": "['我', '要', '找', '药', '膏']",
 948 |   "labeled entities": "[(3, 4, 'cp')]"
 949 |  },
 950 |  {
 951 |   "sentence": "['踩', '脚', '袜', '薄', '绒']",
 952 |   "labeled entities": "[(0, 2, 'cp')]"
 953 |  },
 954 |  {
 955 |   "sentence": "['我', '要', '买', 's', 'p', '6', '8']",
 956 |   "labeled entities": "[(3, 6, 'pp')]"
 957 |  },
 958 |  {
 959 |   "sentence": "['小', '米', 'n', 'a', 'o', 't', 'e', '2']",
 960 |   "labeled entities": "[(0, 1, 'pp')]"
 961 |  },
 962 |  {
 963 |   "sentence": "['月', '经']",
 964 |   "labeled entities": "[]"
 965 |  },
 966 |  {
 967 |   "sentence": "['五', '香', '红', '烧', '牛', '肉']",
 968 |   "labeled entities": "[(4, 5, 'cp')]"
 969 |  },
 970 |  {
 971 |   "sentence": "['睡', '吧']",
 972 |   "labeled entities": "[]"
 973 |  },
 974 |  {
 975 |   "sentence": "['有', '木', '有', '睫', '毛', '增', '长', '液']",
 976 |   "labeled entities": "[(3, 7, 'cp')]"
 977 |  },
 978 |  {
 979 |   "sentence": "['我', '要', '秋', '天', '的']",
 980 |   "labeled entities": "[]"
 981 |  },
 982 |  {
 983 |   "sentence": "['我', '想', '买', '裙', '子']",
 984 |   "labeled entities": "[(3, 4, 'cp')]"
 985 |  },
 986 |  {
 987 |   "sentence": "['Z', 'p', 'p', 'o', ' ', '火', '机']",
 988 |   "labeled entities": "[(0, 3, 'pp'), (5, 6, 'cp')]"
 989 |  },
 990 |  {
 991 |   "sentence": "['6', '0', '0', '左', '右', '的', '显', '卡']",
 992 |   "labeled entities": "[(6, 7, 'cp')]"
 993 |  },
 994 |  {
 995 |   "sentence": "['手', '提', '包', '斜', '挎', '包']",
 996 |   "labeled entities": "[(0, 2, 'cp'), (3, 5, 'cp')]"
 997 |  },
 998 |  {
 999 |   "sentence": "['想', '买', '一', '个', '这', '种', '床', '，', '网', '上', '下', '不', '了', '单']",
1000 |   "labeled entities": "[(6, 6, 'cp')]"
1001 |  },
1002 |  {
1003 |   "sentence": "['便', '宜', '好', '吃', '的', '水', '果']",
1004 |   "labeled entities": "[(5, 6, 'cp')]"
1005 |  },
1006 |  {
1007 |   "sentence": "['买', '手', '机', '膜', '的']",
1008 |   "labeled entities": "[(1, 3, 'cp')]"
1009 |  },
1010 |  {
1011 |   "sentence": "['3', '.', '2', '1']",
1012 |   "labeled entities": "[]"
1013 |  },
1014 |  {
1015 |   "sentence": "['正', '品', '凤', '凰', '自', '行', '车']",
1016 |   "labeled entities": "[(2, 3, 'pp'), (4, 6, 'cp')]"
1017 |  },
1018 |  {
1019 |   "sentence": "['送', '什', '么', '生', '日', '礼', '物', '比', '较', '好', '呢']",
1020 |   "labeled entities": "[]"
1021 |  },
1022 |  {
1023 |   "sentence": "['贵', '货', '叶', '插', '苗']",
1024 |   "labeled entities": "[(2, 4, 'cp')]"
1025 |  },
1026 |  {
1027 |   "sentence": "['我', '要', '买', '中', '长', '款', '棉', '袄']",
1028 |   "labeled entities": "[(6, 7, 'cp')]"
1029 |  },
1030 |  {
1031 |   "sentence": "['韩', '版', '的']",
1032 |   "labeled entities": "[]"
1033 |  },
1034 |  {
1035 |   "sentence": "['要', '哺', '乳', '衣']",
1036 |   "labeled entities": "[(1, 3, 'cp')]"
1037 |  },
1038 |  {
1039 |   "sentence": "['保', '暖', '针', '织', '衫', '内', '搭']",
1040 |   "labeled entities": "[(2, 4, 'cp')]"
1041 |  },
1042 |  {
1043 |   "sentence": "['去', '斑']",
1044 |   "labeled entities": "[]"
1045 |  },
1046 |  {
1047 |   "sentence": "['简', '单', '，', '好', '看', '的', '贴', '纸']",
1048 |   "labeled entities": "[(6, 7, 'cp')]"
1049 |  },
1050 |  {
1051 |   "sentence": "['我', '想', '买', '个', '飞', '行', '器']",
1052 |   "labeled entities": "[(4, 6, 'cp')]"
1053 |  },
1054 |  {
1055 |   "sentence": "['洋', '气', '点', '的', '牛', '仔', '裤']",
1056 |   "labeled entities": "[(4, 6, 'cp')]"
1057 |  },
1058 |  {
1059 |   "sentence": "['有', '没', '有', '棉', '麻', '的', '外', '套']",
1060 |   "labeled entities": "[(3, 4, 'yl'), (6, 7, 'cp')]"
1061 |  },
1062 |  {
1063 |   "sentence": "['增', '粗', '增', '长']",
1064 |   "labeled entities": "[]"
1065 |  },
1066 |  {
1067 |   "sentence": "['手', '机', '偏', '振', '镜', '头']",
1068 |   "labeled entities": "[(0, 1, 'cp'), (2, 5, 'cp')]"
1069 |  },
1070 |  {
1071 |   "sentence": "['一', '周', '岁', '女', '宝']",
1072 |   "labeled entities": "[]"
1073 |  },
1074 |  {
1075 |   "sentence": "['柔', '顺', '剂']",
1076 |   "labeled entities": "[(0, 2, 'cp')]"
1077 |  },
1078 |  {
1079 |   "sentence": "['我', '想', '买', '个', '卧', '蚕', '笔']",
1080 |   "labeled entities": "[(4, 6, 'cp')]"
1081 |  },
1082 |  {
1083 |   "sentence": "['我', '想', '看', '一', '下', '十', '月', '二', '月', '份', '镜', '买', '什', '么', '了']",
1084 |   "labeled entities": "[]"
1085 |  },
1086 |  {
1087 |   "sentence": "['哺', '乳', '运', '动', '装']",
1088 |   "labeled entities": "[(2, 4, 'cp')]"
1089 |  },
1090 |  {
1091 |   "sentence": "['买', '联', '想', '手', '机']",
1092 |   "labeled entities": "[(1, 2, 'pp'), (3, 4, 'cp')]"
1093 |  },
1094 |  {
1095 |   "sentence": "['夏', '季', '的', '半', '袖', '之', '类', '的']",
1096 |   "labeled entities": "[]"
1097 |  },
1098 |  {
1099 |   "sentence": "['母', '女', '装', ' ', '夏', '款']",
1100 |   "labeled entities": "[(0, 2, 'cp')]"
1101 |  },
1102 |  {
1103 |   "sentence": "['御', '泥', '坊', '的']",
1104 |   "labeled entities": "[(0, 2, 'pp')]"
1105 |  },
1106 |  {
1107 |   "sentence": "['情', '侣', '纯', '色', '手', '机', '壳']",
1108 |   "labeled entities": "[(4, 6, 'cp')]"
1109 |  },
1110 |  {
1111 |   "sentence": "['这', '款', '裙', '的', '布', '料', '有', '没', '有', '乔', '其', '纱', '？']",
1112 |   "labeled entities": "[(2, 2, 'cp')]"
1113 |  },
1114 |  {
1115 |   "sentence": "['阔', '腿', '短', '裤']",
1116 |   "labeled entities": "[(0, 3, 'cp')]"
1117 |  },
1118 |  {
1119 |   "sentence": "['要', '买', '一', '个', '魔', '幻', '陀', '螺']",
1120 |   "labeled entities": "[(4, 7, 'cp')]"
1121 |  },
1122 |  {
1123 |   "sentence": "['不', '是', '大', '妈']",
1124 |   "labeled entities": "[]"
1125 |  },
1126 |  {
1127 |   "sentence": "['风', '扇', '灯']",
1128 |   "labeled entities": "[(0, 2, 'cp')]"
1129 |  },
1130 |  {
1131 |   "sentence": "['聚', '拢', '型', '内', '衣']",
1132 |   "labeled entities": "[(3, 4, 'cp')]"
1133 |  },
1134 |  {
1135 |   "sentence": "['8', 'g', '的']",
1136 |   "labeled entities": "[(0, 1, 'gg')]"
1137 |  },
1138 |  {
1139 |   "sentence": "['2', '0', '1', '7', '新', '款', '打', '底', '衫', '可', '外', '穿']",
1140 |   "labeled entities": "[(6, 8, 'cp')]"
1141 |  },
1142 |  {
1143 |   "sentence": "['脚', '垫']",
1144 |   "labeled entities": "[(0, 1, 'cp')]"
1145 |  },
1146 |  {
1147 |   "sentence": "['买', '游', '戏', '本']",
1148 |   "labeled entities": "[(1, 3, 'cp')]"
1149 |  },
1150 |  {
1151 |   "sentence": "['坡', '跟', '鞋', '女']",
1152 |   "labeled entities": "[(0, 2, 'cp')]"
1153 |  },
1154 |  {
1155 |   "sentence": "['想', '要', '一', '个', '能', '装', '鞋', '的', '旅', '行', '包']",
1156 |   "labeled entities": "[(8, 10, 'cp')]"
1157 |  },
1158 |  {
1159 |   "sentence": "['我', '想', '要', '脱', '毛', '膏']",
1160 |   "labeled entities": "[(3, 5, 'cp')]"
1161 |  },
1162 |  {
1163 |   "sentence": "['陈', '皮', '糖']",
1164 |   "labeled entities": "[(0, 2, 'cp')]"
1165 |  },
1166 |  {
1167 |   "sentence": "['熊', '娃', '娃']",
1168 |   "labeled entities": "[(0, 2, 'cp')]"
1169 |  },
1170 |  {
1171 |   "sentence": "['买', '补', '水', '套', '装']",
1172 |   "labeled entities": "[(1, 4, 'cp')]"
1173 |  },
1174 |  {
1175 |   "sentence": "['男', '士', '个', '性', '口', '罩']",
1176 |   "labeled entities": "[(4, 5, 'cp')]"
1177 |  },
1178 |  {
1179 |   "sentence": "['凉', '鞋', '露', '面', '的']",
1180 |   "labeled entities": "[(0, 1, 'cp')]"
1181 |  },
1182 |  {
1183 |   "sentence": "['想', '买', '小', '车']",
1184 |   "labeled entities": "[(3, 3, 'cp')]"
1185 |  },
1186 |  {
1187 |   "sentence": "['二', '年', '级', '买', '什', '么', '故', '事', '比', '较', '好']",
1188 |   "labeled entities": "[]"
1189 |  },
1190 |  {
1191 |   "sentence": "['你', '感', '觉', '什', '么', '手', '机', '好', '用']",
1192 |   "labeled entities": "[(5, 6, 'cp')]"
1193 |  },
1194 |  {
1195 |   "sentence": "['新', '款', '休', '闲', '装']",
1196 |   "labeled entities": "[(2, 4, 'cp')]"
1197 |  },
1198 |  {
1199 |   "sentence": "['春', '装', '外']",
1200 |   "labeled entities": "[]"
1201 |  },
1202 |  {
1203 |   "sentence": "['我', '要', '的', '是', '力', '帆', '欧', '式', '战', '马', 'A', '6', '的', '立', '柱', '包', '角']",
1204 |   "labeled entities": "[(4, 5, 'pp'), (6, 11, 'xh'), (13, 16, 'cp')]"
1205 |  },
1206 |  {
1207 |   "sentence": "['培', '训', '班', '自', '粘', '壁', '纸']",
1208 |   "labeled entities": "[(3, 6, 'cp')]"
1209 |  },
1210 |  {
1211 |   "sentence": "['溥', '长', '袖']",
1212 |   "labeled entities": "[]"
1213 |  },
1214 |  {
1215 |   "sentence": "['好', '吃', '又', '便', '宜', '的', '零', '食']",
1216 |   "labeled entities": "[(6, 7, 'cp')]"
1217 |  },
1218 |  {
1219 |   "sentence": "['秋', '季', '整', '套', '运', '动', '装']",
1220 |   "labeled entities": "[(4, 6, 'cp')]"
1221 |  },
1222 |  {
1223 |   "sentence": "['清', '朝', '女', '士', '秋', '衣']",
1224 |   "labeled entities": "[(4, 5, 'cp')]"
1225 |  },
1226 |  {
1227 |   "sentence": "['淡', '水', '养', '殖', '小', '鱼']",
1228 |   "labeled entities": "[(5, 5, 'cp')]"
1229 |  },
1230 |  {
1231 |   "sentence": "['白', '熊', '啤', '酒', '六', '瓶']",
1232 |   "labeled entities": "[(0, 1, 'pp'), (2, 3, 'cp'), (4, 5, 'gg')]"
1233 |  },
1234 |  {
1235 |   "sentence": "['毛', '呢', '外', '衣']",
1236 |   "labeled entities": "[(2, 3, 'cp')]"
1237 |  },
1238 |  {
1239 |   "sentence": "['男', '士', '外', '套', '韩', '版', '修', '身']",
1240 |   "labeled entities": "[(2, 3, 'cp')]"
1241 |  },
1242 |  {
1243 |   "sentence": "['床', '垫', '薄', '的']",
1244 |   "labeled entities": "[(0, 1, 'cp')]"
1245 |  },
1246 |  {
1247 |   "sentence": "['九', '鱼', '图']",
1248 |   "labeled entities": "[(0, 2, 'cp')]"
1249 |  },
1250 |  {
1251 |   "sentence": "['想', '买', '男', '款', '能', '量', '吊', '坠']",
1252 |   "labeled entities": "[(6, 7, 'cp')]"
1253 |  },
1254 |  {
1255 |   "sentence": "['g']",
1256 |   "labeled entities": "[]"
1257 |  },
1258 |  {
1259 |   "sentence": "['男', '生', '内', '裤']",
1260 |   "labeled entities": "[(2, 3, 'cp')]"
1261 |  },
1262 |  {
1263 |   "sentence": "['手', '链', '纯', '银', '配', '件']",
1264 |   "labeled entities": "[(0, 1, 'cp'), (2, 3, 'yl'), (4, 5, 'cp')]"
1265 |  },
1266 |  {
1267 |   "sentence": "['买', '三', '文', '鱼', '送', '芥', '末', '嘛', '？']",
1268 |   "labeled entities": "[(1, 3, 'cp'), (5, 6, 'cp')]"
1269 |  },
1270 |  {
1271 |   "sentence": "['h', 'o', 'l', 'l', 'e', 'K', 'e', 'i', 't', 'h', '贴', '纸']",
1272 |   "labeled entities": "[(0, 9, 'pp'), (10, 11, 'cp')]"
1273 |  },
1274 |  {
1275 |   "sentence": "['外', '套', ' ', '男']",
1276 |   "labeled entities": "[(0, 1, 'cp')]"
1277 |  },
1278 |  {
1279 |   "sentence": "['女', '孩', '到', '7', '岁', '的', '肖']",
1280 |   "labeled entities": "[]"
1281 |  },
1282 |  {
1283 |   "sentence": "['我', '要', '买', '宿', '舍', '电', '脑', '桌']",
1284 |   "labeled entities": "[(5, 7, 'cp')]"
1285 |  },
1286 |  {
1287 |   "sentence": "['要', '儿', '童', '的']",
1288 |   "labeled entities": "[]"
1289 |  },
1290 |  {
1291 |   "sentence": "['裙', '撑']",
1292 |   "labeled entities": "[(0, 1, 'cp')]"
1293 |  },
1294 |  {
1295 |   "sentence": "['针', '织', '马', '甲']",
1296 |   "labeled entities": "[(2, 3, 'cp')]"
1297 |  },
1298 |  {
1299 |   "sentence": "['打', '游', '戏']",
1300 |   "labeled entities": "[]"
1301 |  },
1302 |  {
1303 |   "sentence": "['胖', 'M', 'M', '裤', '子']",
1304 |   "labeled entities": "[(3, 4, 'cp')]"
1305 |  },
1306 |  {
1307 |   "sentence": "['不', '增', '高', ' ', '便', '宜', '点', '的']",
1308 |   "labeled entities": "[]"
1309 |  },
1310 |  {
1311 |   "sentence": "['我', '要', '买', '宝', '宝', '补', '钙', '的']",
1312 |   "labeled entities": "[]"
1313 |  },
1314 |  {
1315 |   "sentence": "['辣', '妈', '姜', '糖', '膏']",
1316 |   "labeled entities": "[(2, 4, 'cp')]"
1317 |  },
1318 |  {
1319 |   "sentence": "['是', '门', '不', '是', '锁']",
1320 |   "labeled entities": "[(1, 1, 'cp'), (4, 4, 'cp')]"
1321 |  },
1322 |  {
1323 |   "sentence": "['我', '今', '天', '在', '淘', '宝', '里', '想', '买', '一', '件', '内', '衣', '，', '还', '没', '有', '下', '单', '前', '咨', '询', '了', '那', '家', '店', '的', '客', '服', '，', '她', '说', '我', '差', '评', '太', '多', '，', '不', '卖', '给', '我', '，', '还', '出', '口', '伤', '人', '的', '骂', '我', '，', '我', '想', '投', '诉', '她', '态', '度', '恶', '劣']",
1324 |   "labeled entities": "[(11, 12, 'cp')]"
1325 |  },
1326 |  {
1327 |   "sentence": "['我', '要', '买', '懒', '蛋', '蛋']",
1328 |   "labeled entities": "[]"
1329 |  },
1330 |  {
1331 |   "sentence": "['我', '要', '刚', '才', '给', '你', '发', '的', '电', '灯', '充', '电', '器']",
1332 |   "labeled entities": "[(8, 12, 'cp')]"
1333 |  },
1334 |  {
1335 |   "sentence": "['我', '想', '买', '个', '排', '毒', '养', '颜', '的', '，', '因', '为', '现', '在', '给', '宝', '宝', '吃', '奶', '不', '知', '道', '可', '以', '用', '哪', '款']",
1336 |   "labeled entities": "[]"
1337 |  },
1338 |  {
1339 |   "sentence": "['百', '搭', '衣', '服', '女']",
1340 |   "labeled entities": "[(2, 3, 'cp')]"
1341 |  },
1342 |  {
1343 |   "sentence": "['有', '没', '有', '什', '么', '香', '水', '适', '合', '三', '周', '大', '的', '宠', '物', '兔', '用']",
1344 |   "labeled entities": "[(5, 6, 'cp')]"
1345 |  },
1346 |  {
1347 |   "sentence": "['问', '你', '事', '儿', '粉', '色', '不', '是', '红', '色', '了']",
1348 |   "labeled entities": "[]"
1349 |  },
1350 |  {
1351 |   "sentence": "['我', '想', '要', '春', '天', '的', '外', '套']",
1352 |   "labeled entities": "[(6, 7, 'cp')]"
1353 |  },
1354 |  {
1355 |   "sentence": "['是', '买', '的', '花', '颜', '色', '不', '对']",
1356 |   "labeled entities": "[(3, 3, 'cp')]"
1357 |  },
1358 |  {
1359 |   "sentence": "['看', '一', '下', '苹', '果', '7']",
1360 |   "labeled entities": "[(3, 4, 'pp'), (5, 5, 'xh')]"
1361 |  },
1362 |  {
1363 |   "sentence": "['想', '买', '睡', '衣', '，', '但', '是', '又', '怕', '短', '了']",
1364 |   "labeled entities": "[(2, 3, 'cp')]"
1365 |  },
1366 |  {
1367 |   "sentence": "['这', '个', '颜', '色', '的', '开', '衫', '外', '搭', '配', '什', '么', '样', '，', '的', '什', '么', '样', '的', '颜', '色', '的', '裙', '子', '，', '好', '看']",
1368 |   "labeled entities": "[(5, 6, 'cp'), (22, 23, 'cp')]"
1369 |  },
1370 |  {
1371 |   "sentence": "['夏', '季', '学', '生', '长', '裙']",
1372 |   "labeled entities": "[(4, 5, 'cp')]"
1373 |  },
1374 |  {
1375 |   "sentence": "['胖', '妹', '女', '装']",
1376 |   "labeled entities": "[(2, 3, 'cp')]"
1377 |  },
1378 |  {
1379 |   "sentence": "['万', '家', '林', '空', '气', '清', '新', '机']",
1380 |   "labeled entities": "[(0, 2, 'pp'), (3, 7, 'cp')]"
1381 |  },
1382 |  {
1383 |   "sentence": "['黄', '金']",
1384 |   "labeled entities": "[(0, 1, 'cp')]"
1385 |  },
1386 |  {
1387 |   "sentence": "['在', '干', '嘛', '干', '嘛', '，', '不', '没', '有', '书', '，', '8', '斤', '要', '那', '个', '拉', '杆', '吃']",
1388 |   "labeled entities": "[]"
1389 |  },
1390 |  {
1391 |   "sentence": "['苹', '果', '笔', '记', '本']",
1392 |   "labeled entities": "[(0, 1, 'pp'), (2, 4, 'cp')]"
1393 |  },
1394 |  {
1395 |   "sentence": "['海', '底', '捞', '火', '锅', '料']",
1396 |   "labeled entities": "[(3, 5, 'cp')]"
1397 |  },
1398 |  {
1399 |   "sentence": "['就', '我', '想', '买', '那', '个', '表', ' ', '下', '面', '就', '有']",
1400 |   "labeled entities": "[(6, 6, 'cp')]"
1401 |  },
1402 |  {
1403 |   "sentence": "['我', '要', '买', '皮', '裙']",
1404 |   "labeled entities": "[(3, 4, 'cp')]"
1405 |  },
1406 |  {
1407 |   "sentence": "['夏', '天', '拉', '拉', '裤']",
1408 |   "labeled entities": "[(2, 4, 'cp')]"
1409 |  },
1410 |  {
1411 |   "sentence": "['推', '荐', '一', '款', '性', '价', '比', '高', '，', '不', '易', '脱', '妆', '的', '气', '垫']",
1412 |   "labeled entities": "[(14, 15, 'cp')]"
1413 |  },
1414 |  {
1415 |   "sentence": "['魔', '方', '三', '级']",
1416 |   "labeled entities": "[(0, 1, 'cp')]"
1417 |  },
1418 |  {
1419 |   "sentence": "['5', '寸', '屏', '的', 'v', 'i', 'v', 'o', '手', '机']",
1420 |   "labeled entities": "[(0, 1, 'gg'), (4, 7, 'pp'), (8, 9, 'cp')]"
1421 |  },
1422 |  {
1423 |   "sentence": "['多', '平', '台']",
1424 |   "labeled entities": "[]"
1425 |  },
1426 |  {
1427 |   "sentence": "['自', '粘', '书', '皮']",
1428 |   "labeled entities": "[(2, 3, 'cp')]"
1429 |  },
1430 |  {
1431 |   "sentence": "['雪', '宝', '毛', '绒', '毕', '业', '玩', '具']",
1432 |   "labeled entities": "[(0, 1, 'pp'), (6, 7, 'cp')]"
1433 |  },
1434 |  {
1435 |   "sentence": "['什', '么', '牌', '子', '的', '睡', '衣', '好']",
1436 |   "labeled entities": "[(5, 6, 'cp')]"
1437 |  },
1438 |  {
1439 |   "sentence": "['我', '买', '水', '果']",
1440 |   "labeled entities": "[(2, 3, 'cp')]"
1441 |  },
1442 |  {
1443 |   "sentence": "['我', '要', '的', '是', '卫', '衣']",
1444 |   "labeled entities": "[(4, 5, 'cp')]"
1445 |  },
1446 |  {
1447 |   "sentence": "['O', 'P', 'P', 'O', ' ', 'A', '3', '1']",
1448 |   "labeled entities": "[(0, 3, 'pp'), (5, 7, 'xh')]"
1449 |  },
1450 |  {
1451 |   "sentence": "['长', '袖', '加', '绒']",
1452 |   "labeled entities": "[]"
1453 |  },
1454 |  {
1455 |   "sentence": "['而', '且', '，', '我', '给', '他', '买', '滴', '，', '是', '聊', '套', '衣', '服']",
1456 |   "labeled entities": "[(12, 13, 'cp')]"
1457 |  },
1458 |  {
1459 |   "sentence": "['婴', '儿', '卫', '衣', '外', '出', '服']",
1460 |   "labeled entities": "[(0, 3, 'cp'), (4, 6, 'cp')]"
1461 |  },
1462 |  {
1463 |   "sentence": "['十', '块', '以', '内', '！', '！']",
1464 |   "labeled entities": "[]"
1465 |  },
1466 |  {
1467 |   "sentence": "['破', '洞', '牛', '仔', '裤', '上', '衣', '搭', '配', '什', '么']",
1468 |   "labeled entities": "[(2, 4, 'cp'), (5, 6, 'cp')]"
1469 |  },
1470 |  {
1471 |   "sentence": "['面', '膜', '是', '睡', '眠', '面', '膜']",
1472 |   "labeled entities": "[(0, 1, 'cp'), (5, 6, 'cp')]"
1473 |  },
1474 |  {
1475 |   "sentence": "['有', '没', '有', '什', '么', '好', '看', '的', '衣', '服', '和', '裤', '子', '呀']",
1476 |   "labeled entities": "[(8, 9, 'cp'), (11, 12, 'cp')]"
1477 |  },
1478 |  {
1479 |   "sentence": "['老', '人', '护', '理', '垫', '，', '卧', '床', '老', '人', '用', '的']",
1480 |   "labeled entities": "[(0, 4, 'cp')]"
1481 |  },
1482 |  {
1483 |   "sentence": "['美', '妆', '工', '具']",
1484 |   "labeled entities": "[(0, 3, 'cp')]"
1485 |  },
1486 |  {
1487 |   "sentence": "['爷', '爷', '8', '0', '大', '寿', ' ', '孙', '女', '该', '送', '什', '么', '礼', '物', '合', '适', '？']",
1488 |   "labeled entities": "[]"
1489 |  },
1490 |  {
1491 |   "sentence": "['大', '王', '天', '使']",
1492 |   "labeled entities": "[(0, 1, 'pp'), (2, 3, 'xh')]"
1493 |  },
1494 |  {
1495 |   "sentence": "['我', '想', '要', '情', '侣', '鞋']",
1496 |   "labeled entities": "[(3, 5, 'cp')]"
1497 |  },
1498 |  {
1499 |   "sentence": "['女', '人', '补', '血', '，', '买', '什', '么', '药']",
1500 |   "labeled entities": "[(8, 8, 'cp')]"
1501 |  },
1502 |  {
1503 |   "sentence": "['我', '要', '买', '硬', '盘']",
1504 |   "labeled entities": "[(3, 4, 'cp')]"
1505 |  },
1506 |  {
1507 |   "sentence": "['斜', '背', '小', '包', '女']",
1508 |   "labeled entities": "[(3, 3, 'cp')]"
1509 |  },
1510 |  {
1511 |   "sentence": "['春', '秋', ' ', '上', '衣', ' ', '打', '底', '衫', ' ', 'T', '恤', '衫']",
1512 |   "labeled entities": "[(3, 4, 'cp'), (6, 8, 'cp'), (10, 12, 'cp')]"
1513 |  },
1514 |  {
1515 |   "sentence": "['显', '瘦', '连', '衣', '长', '裙']",
1516 |   "labeled entities": "[(2, 5, 'cp')]"
1517 |  },
1518 |  {
1519 |   "sentence": "['我', '想', '买', '东', '西', '可', '是', '淘', '宝', '地', '址', '填', '不', '到', '这', '里', '啊']",
1520 |   "labeled entities": "[]"
1521 |  },
1522 |  {
1523 |   "sentence": "['浅', '蓝', '色', '牛', '仔', '外', '套', '女', '装', '2', '0', '1', '7', '新', '款']",
1524 |   "labeled entities": "[(3, 4, 'yl'), (5, 6, 'cp'), (7, 8, 'cp')]"
1525 |  },
1526 |  {
1527 |   "sentence": "['芝', '士']",
1528 |   "labeled entities": "[(0, 1, 'cp')]"
1529 |  },
1530 |  {
1531 |   "sentence": "['超', '薄', '胸', '罩']",
1532 |   "labeled entities": "[(2, 3, 'cp')]"
1533 |  },
1534 |  {
1535 |   "sentence": "['我', '还', '想', '买', '我', '买', '过', '的', '水', '壶']",
1536 |   "labeled entities": "[(8, 9, 'cp')]"
1537 |  },
1538 |  {
1539 |   "sentence": "['我', '要', '买', '女', '生', '穿', '的', '单', '鞋']",
1540 |   "labeled entities": "[(7, 8, 'cp')]"
1541 |  },
1542 |  {
1543 |   "sentence": "['我', '想', '要', '中', '年', '加', '肥', '女', '春', '装']",
1544 |   "labeled entities": "[(8, 9, 'cp')]"
1545 |  },
1546 |  {
1547 |   "sentence": "['我', '想', '买', '丰', '田', '考', '斯', '特', '的', '操', '作', '台', '，', '防', '光', '垫', '儿', '为', '什', '么', '咱', '们', '这', '没', '有', '呢', '，', '是', '没', '上', '架', '是', '怎', '么', '回', '事', '儿']",
1548 |   "labeled entities": "[(3, 7, 'cp'), (9, 11, 'cp'), (13, 15, 'cp')]"
1549 |  },
1550 |  {
1551 |   "sentence": "['春', '季', '套', '装', '韩', '版', '，']",
1552 |   "labeled entities": "[(2, 3, 'cp')]"
1553 |  },
1554 |  {
1555 |   "sentence": "['美', '容', '床']",
1556 |   "labeled entities": "[(0, 2, 'cp')]"
1557 |  },
1558 |  {
1559 |   "sentence": "['6', '0', '0', '0', '以', '上']",
1560 |   "labeled entities": "[]"
1561 |  },
1562 |  {
1563 |   "sentence": "['青', '年', '男', '装']",
1564 |   "labeled entities": "[(2, 3, 'cp')]"
1565 |  },
1566 |  {
1567 |   "sentence": "['8', 'G', '内', '存', '条']",
1568 |   "labeled entities": "[(0, 1, 'gg'), (2, 4, 'cp')]"
1569 |  },
1570 |  {
1571 |   "sentence": "['敏', '感', '护', '肤']",
1572 |   "labeled entities": "[]"
1573 |  },
1574 |  {
1575 |   "sentence": "['胖', 'm', 'm', '喇', '叭', '牛', '仔', '裤', '卖', '一', '送', '一']",
1576 |   "labeled entities": "[(5, 7, 'cp')]"
1577 |  },
1578 |  {
1579 |   "sentence": "['1', '0', '0', '0', '~', '3', '0', '0', '0']",
1580 |   "labeled entities": "[]"
1581 |  },
1582 |  {
1583 |   "sentence": "['剃', '须', '刀', '电', '路', '板']",
1584 |   "labeled entities": "[(0, 5, 'cp')]"
1585 |  },
1586 |  {
1587 |   "sentence": "['u', '型', '简', '欧', '沙', '发']",
1588 |   "labeled entities": "[(4, 5, 'cp')]"
1589 |  },
1590 |  {
1591 |   "sentence": "['老', '板', '椅']",
1592 |   "labeled entities": "[(0, 2, 'cp')]"
1593 |  },
1594 |  {
1595 |   "sentence": "['有', '没', '有', '电', '动', '的', '伸', '缩', '蚊', '帐', '吗', '？']",
1596 |   "labeled entities": "[(8, 9, 'cp')]"
1597 |  },
1598 |  {
1599 |   "sentence": "['二', '锅', '头', '多', '少', '钱']",
1600 |   "labeled entities": "[(0, 2, 'cp')]"
1601 |  },
1602 |  {
1603 |   "sentence": "['牙', '膏', '美', '白', '多', '少', '钱']",
1604 |   "labeled entities": "[(0, 1, 'cp')]"
1605 |  },
1606 |  {
1607 |   "sentence": "['气', '泡', '矿', '泉', '水', '多', '少', '钱']",
1608 |   "labeled entities": "[(0, 4, 'cp')]"
1609 |  },
1610 |  {
1611 |   "sentence": "['我', '要', '买', '金', '领', '冠', '珍', '护']",
1612 |   "labeled entities": "[(3, 7, 'cp')]"
1613 |  },
1614 |  {
1615 |   "sentence": "['修', '身', '的', '裙', '子']",
1616 |   "labeled entities": "[(3, 4, 'cp')]"
1617 |  },
1618 |  {
1619 |   "sentence": "['我', '要', '买', '灭', '蚊', '水']",
1620 |   "labeled entities": "[(3, 5, 'cp')]"
1621 |  },
1622 |  {
1623 |   "sentence": "['微', '尔', '多', '少', '钱']",
1624 |   "labeled entities": "[(0, 1, 'pp')]"
1625 |  },
1626 |  {
1627 |   "sentence": "['我', '要', '买', '眼', '镜', '小', '猫', '瓜', '子']",
1628 |   "labeled entities": "[(3, 6, 'pp'), (7, 8, 'cp')]"
1629 |  },
1630 |  {
1631 |   "sentence": "['沙', '士', '多', '少', '钱']",
1632 |   "labeled entities": "[(0, 1, 'cp')]"
1633 |  },
1634 |  {
1635 |   "sentence": "['我', '要', '买', '蓝', '月', '亮', '漂', '白', '水']",
1636 |   "labeled entities": "[(3, 5, 'pp'), (6, 8, 'cp')]"
1637 |  },
1638 |  {
1639 |   "sentence": "['光', '明', '优', '多', '少', '钱']",
1640 |   "labeled entities": "[(0, 1, 'pp'), (2, 2, 'xh')]"
1641 |  },
1642 |  {
1643 |   "sentence": "['米', '饭', '速', '食', '多', '少', '钱']",
1644 |   "labeled entities": "[(0, 1, 'cp')]"
1645 |  },
1646 |  {
1647 |   "sentence": "['我', '要', '买', '酥', '性', '饼', '干']",
1648 |   "labeled entities": "[(3, 6, 'cp')]"
1649 |  },
1650 |  {
1651 |   "sentence": "['我', '要', '买', '吊', '床']",
1652 |   "labeled entities": "[(3, 4, 'cp')]"
1653 |  },
1654 |  {
1655 |   "sentence": "['我', '要', '买', '蔬', '菜', '沙', '拉', '即', '食']",
1656 |   "labeled entities": "[(3, 4, 'yl'), (5, 6, 'cp')]"
1657 |  },
1658 |  {
1659 |   "sentence": "['疏', '通', '剂', '多', '少', '钱']",
1660 |   "labeled entities": "[(0, 2, 'cp')]"
1661 |  },
1662 |  {
1663 |   "sentence": "['我', '要', '买', '凉', '枕', '头']",
1664 |   "labeled entities": "[(3, 5, 'cp')]"
1665 |  },
1666 |  {
1667 |   "sentence": "['我', '要', '买', '抽', '取', '式', '卫', '生', '纸']",
1668 |   "labeled entities": "[(6, 8, 'cp')]"
1669 |  },
1670 |  {
1671 |   "sentence": "['我', '要', '买', '荞', '麦', '面', '条', ' ', '荞', '麦', '挂', '面']",
1672 |   "labeled entities": "[(3, 4, 'yl'), (5, 6, 'cp'), (8, 9, 'yl'), (10, 11, 'cp')]"
1673 |  },
1674 |  {
1675 |   "sentence": "['我', '要', '买', '凉', '鞋']",
1676 |   "labeled entities": "[(3, 4, 'cp')]"
1677 |  },
1678 |  {
1679 |   "sentence": "['上', '好', '佳', '多', '少', '钱']",
1680 |   "labeled entities": "[(0, 2, 'pp')]"
1681 |  },
1682 |  {
1683 |   "sentence": "['糙', '米', '多', '少', '钱']",
1684 |   "labeled entities": "[(0, 1, 'cp')]"
1685 |  },
1686 |  {
1687 |   "sentence": "['我', '要', '买', '盐', '津']",
1688 |   "labeled entities": "[(3, 4, 'cp')]"
1689 |  },
1690 |  {
1691 |   "sentence": "['我', '要', '买', '甲', '醛', '检', '测', '仪']",
1692 |   "labeled entities": "[(3, 7, 'cp')]"
1693 |  },
1694 |  {
1695 |   "sentence": "['我', '要', '买', '口', '红']",
1696 |   "labeled entities": "[(3, 4, 'cp')]"
1697 |  },
1698 |  {
1699 |   "sentence": "['张', '贴', '面', '膜']",
1700 |   "labeled entities": "[(2, 3, 'cp')]"
1701 |  },
1702 |  {
1703 |   "sentence": "['麦', '克', '风']",
1704 |   "labeled entities": "[(0, 2, 'cp')]"
1705 |  },
1706 |  {
1707 |   "sentence": "['我', '要', '买', '豆', '豉', '鱼', '罐', '头']",
1708 |   "labeled entities": "[(3, 4, 'yl'), (5, 7, 'cp')]"
1709 |  },
1710 |  {
1711 |   "sentence": "['银', '耳', ' ', '糯', '耳', '多', '少', '钱']",
1712 |   "labeled entities": "[(0, 1, 'cp'), (3, 4, 'cp')]"
1713 |  },
1714 |  {
1715 |   "sentence": "['我', '要', '买', '特', '色', '小', '吃']",
1716 |   "labeled entities": "[(3, 6, 'cp')]"
1717 |  },
1718 |  {
1719 |   "sentence": "['我', '要', '买', '灭', '蚊', '拍', '电', '蚊', '子', '拍']",
1720 |   "labeled entities": "[(3, 5, 'cp'), (6, 9, 'cp')]"
1721 |  },
1722 |  {
1723 |   "sentence": "['金', '装', '清', '风', '多', '少', '钱']",
1724 |   "labeled entities": "[(2, 3, 'cp')]"
1725 |  },
1726 |  {
1727 |   "sentence": "['凑', '单', '多', '少', '钱']",
1728 |   "labeled entities": "[]"
1729 |  },
1730 |  {
1731 |   "sentence": "['我', '要', '买', '秋', '衣']",
1732 |   "labeled entities": "[(3, 4, 'cp')]"
1733 |  },
1734 |  {
1735 |   "sentence": "['我', '要', '买', '喷', '雾', '瓶']",
1736 |   "labeled entities": "[(3, 5, 'cp')]"
1737 |  },
1738 |  {
1739 |   "sentence": "['我', '要', '买', '楼', '兰', '蜜', '语', '红', '枣']",
1740 |   "labeled entities": "[(3, 6, 'pp'), (7, 8, 'cp')]"
1741 |  },
1742 |  {
1743 |   "sentence": "['诺', '基', '亚']",
1744 |   "labeled entities": "[(0, 2, 'pp')]"
1745 |  },
1746 |  {
1747 |   "sentence": "['消', '化', '全', '麦', '饼', '干', '多', '少', '钱']",
1748 |   "labeled entities": "[(2, 3, 'yl'), (4, 5, 'cp')]"
1749 |  },
1750 |  {
1751 |   "sentence": "['我', '要', '买', '罗', '兰', '香', '皂']",
1752 |   "labeled entities": "[(3, 4, 'pp'), (5, 6, 'cp')]"
1753 |  },
1754 |  {
1755 |   "sentence": "['脱', '脂', '牛', '奶', '1', 'l', ' ', '1', '2', '盒', ' ', '箱', '多', '少', '钱']",
1756 |   "labeled entities": "[(0, 3, 'cp'), (4, 5, 'gg'), (7, 9, 'gg'), (11, 11, 'gg')]"
1757 |  },
1758 |  {
1759 |   "sentence": "['鲜', '水', '果', '多', '少', '钱']",
1760 |   "labeled entities": "[(0, 2, 'cp')]"
1761 |  },
1762 |  {
1763 |   "sentence": "['我', '要', '买', '拔', '丝', '肉', '松', '蛋', '糕']",
1764 |   "labeled entities": "[]"
1765 |  },
1766 |  {
1767 |   "sentence": "['我', '要', '买', '小', '鱿', '鱼', '仔']",
1768 |   "labeled entities": "[(4, 6, 'cp')]"
1769 |  },
1770 |  {
1771 |   "sentence": "['我', '要', '买', '乡', '乡', '嘴']",
1772 |   "labeled entities": "[(3, 5, 'pp')]"
1773 |  },
1774 |  {
1775 |   "sentence": "['我', '要', '买', '儿', '童', '车', ' ', '三', '轮', '车']",
1776 |   "labeled entities": "[(3, 5, 'cp'), (7, 9, 'cp')]"
1777 |  },
1778 |  {
1779 |   "sentence": "['海', '绵', '拖', '把', '头', ' ', '替', '换', '多', '少', '钱']",
1780 |   "labeled entities": "[(0, 1, 'yl'), (2, 4, 'cp')]"
1781 |  },
1782 |  {
1783 |   "sentence": "['海', '鲜', '零', '食', '多', '少', '钱']",
1784 |   "labeled entities": "[(0, 1, 'yl'), (2, 3, 'cp')]"
1785 |  },
1786 |  {
1787 |   "sentence": "['我', '要', '买', '蒙', '牛', '纯', '牛', '奶', '袋', '装']",
1788 |   "labeled entities": "[(3, 4, 'pp'), (5, 7, 'cp')]"
1789 |  },
1790 |  {
1791 |   "sentence": "['我', '要', '买', '自', '动', '雨', '伞']",
1792 |   "labeled entities": "[(3, 6, 'cp')]"
1793 |  },
1794 |  {
1795 |   "sentence": "['儿', '童', '蚊', '香', '液', ' ', '无', '味', ' ', '婴', '儿', '多', '少', '钱']",
1796 |   "labeled entities": "[(0, 4, 'cp')]"
1797 |  },
1798 |  {
1799 |   "sentence": "['我', '要', '买', '洗', '衣', '皂', '粉']",
1800 |   "labeled entities": "[(3, 6, 'cp')]"
1801 |  },
1802 |  {
1803 |   "sentence": "['好', '奇', '金', '装', '多', '少', '钱']",
1804 |   "labeled entities": "[(0, 1, 'pp'), (2, 3, 'xh')]"
1805 |  },
1806 |  {
1807 |   "sentence": "['奶', '瓶', 'p', 'p', 's', 'u', '多', '少', '钱']",
1808 |   "labeled entities": "[(0, 1, 'cp'), (2, 5, 'yl')]"
1809 |  },
1810 |  {
1811 |   "sentence": "['中', '脉']",
1812 |   "labeled entities": "[(0, 1, 'pp')]"
1813 |  },
1814 |  {
1815 |   "sentence": "['花', '椒', '面', '多', '少', '钱']",
1816 |   "labeled entities": "[(0, 2, 'cp')]"
1817 |  },
1818 |  {
1819 |   "sentence": "['我', '要', '买', '美', '德', '乐', '哺', '乳', '文', '胸']",
1820 |   "labeled entities": "[(3, 5, 'pp'), (6, 9, 'cp')]"
1821 |  },
1822 |  {
1823 |   "sentence": "['我', '要', '买', '天', '猫', '生', '鲜']",
1824 |   "labeled entities": "[(3, 4, 'pp'), (5, 6, 'cp')]"
1825 |  },
1826 |  {
1827 |   "sentence": "['我', '要', '买', '厨', '帮', '酱', '油']",
1828 |   "labeled entities": "[(3, 4, 'pp'), (5, 6, 'cp')]"
1829 |  },
1830 |  {
1831 |   "sentence": "['袋', '装', '鲜', '牛', '奶', '多', '少', '钱']",
1832 |   "labeled entities": "[(0, 1, 'gg'), (2, 4, 'cp')]"
1833 |  },
1834 |  {
1835 |   "sentence": "['大', '头', '菜', '多', '少', '钱']",
1836 |   "labeled entities": "[(0, 2, 'cp')]"
1837 |  },
1838 |  {
1839 |   "sentence": "['儿', '童', ' ', '杯', '多', '少', '钱']",
1840 |   "labeled entities": "[(3, 3, 'cp')]"
1841 |  },
1842 |  {
1843 |   "sentence": "['我', '要', '买', '进', '口', '果', '泥']",
1844 |   "labeled entities": "[(5, 6, 'cp')]"
1845 |  },
1846 |  {
1847 |   "sentence": "['我', '要', '买', '垃', '圾', '袋', '大', '号']",
1848 |   "labeled entities": "[(3, 5, 'cp')]"
1849 |  },
1850 |  {
1851 |   "sentence": "['鸡', '汤', '多', '少', '钱']",
1852 |   "labeled entities": "[(0, 1, 'cp')]"
1853 |  },
1854 |  {
1855 |   "sentence": "['无', '芯', '纸', '多', '少', '钱']",
1856 |   "labeled entities": "[(0, 2, 'cp')]"
1857 |  },
1858 |  {
1859 |   "sentence": "['我', '要', '买', '鱿', '鱼', '足', '片']",
1860 |   "labeled entities": "[(3, 6, 'cp')]"
1861 |  },
1862 |  {
1863 |   "sentence": "['我', '要', '买', '雨', '衣']",
1864 |   "labeled entities": "[(3, 4, 'cp')]"
1865 |  },
1866 |  {
1867 |   "sentence": "['优', '形', '电', '烤', '鸡', '胸', '肉', '片', '多', '少', '钱']",
1868 |   "labeled entities": "[(0, 1, 'pp'), (4, 7, 'cp')]"
1869 |  },
1870 |  {
1871 |   "sentence": "['浪', '莎', '内', '裤', '女', '多', '少', '钱']",
1872 |   "labeled entities": "[(0, 1, 'pp'), (2, 3, 'cp')]"
1873 |  },
1874 |  {
1875 |   "sentence": "['皇', '冠']",
1876 |   "labeled entities": "[(0, 1, 'pp')]"
1877 |  },
1878 |  {
1879 |   "sentence": "['我', '要', '买', '小', '番', '茄', '圣', '女', '果', '西', '红', '柿']",
1880 |   "labeled entities": "[(3, 5, 'cp'), (6, 8, 'cp'), (9, 11, 'cp')]"
1881 |  },
1882 |  {
1883 |   "sentence": "['旋', '转', '拖', '把', '头', '多', '少', '钱']",
1884 |   "labeled entities": "[(0, 4, 'cp')]"
1885 |  },
1886 |  {
1887 |   "sentence": "['我', '要', '买', '细', '砂', '糖', ' ', '烘', '焙']",
1888 |   "labeled entities": "[(3, 5, 'cp')]"
1889 |  },
1890 |  {
1891 |   "sentence": "['我', '要', '买', '酒', '曲', ' ', '米', '酒', '曲', ' ', '甜', '酒', '曲']",
1892 |   "labeled entities": "[(3, 4, 'cp'), (6, 8, 'cp'), (10, 12, 'cp')]"
1893 |  },
1894 |  {
1895 |   "sentence": "['女', '童', '裤', '袜']",
1896 |   "labeled entities": "[(2, 3, 'cp')]"
1897 |  },
1898 |  {
1899 |   "sentence": "['绿', '伞', '洗', '衣', '机', '槽', '清', '洁', '剂', '多', '少', '钱']",
1900 |   "labeled entities": "[(0, 1, 'pp'), (2, 8, 'cp')]"
1901 |  },
1902 |  {
1903 |   "sentence": "['明', '治', '酸', '奶', '多', '少', '钱']",
1904 |   "labeled entities": "[(0, 1, 'pp'), (2, 3, 'cp')]"
1905 |  },
1906 |  {
1907 |   "sentence": "['我', '要', '买', '六', '神', '宝', '宝']",
1908 |   "labeled entities": "[(3, 4, 'pp')]"
1909 |  },
1910 |  {
1911 |   "sentence": "['奥', '妙', '洗', '衣', '粉', '全', '自', '动', '3', 'k', 'g', '多', '少', '钱']",
1912 |   "labeled entities": "[(0, 1, 'pp'), (2, 4, 'cp'), (8, 10, 'gg')]"
1913 |  },
1914 |  {
1915 |   "sentence": "['我', '要', '买', '生', '猪', '肉']",
1916 |   "labeled entities": "[(3, 5, 'cp')]"
1917 |  },
1918 |  {
1919 |   "sentence": "['我', '要', '买', '温', '奶', '器']",
1920 |   "labeled entities": "[(3, 5, 'cp')]"
1921 |  },
1922 |  {
1923 |   "sentence": "['我', '要', '买', '儿', '童', '刷', '牙', '杯', '子']",
1924 |   "labeled entities": "[(5, 7, 'cp')]"
1925 |  },
1926 |  {
1927 |   "sentence": "['我', '要', '买', '泡', '椒', '1']",
1928 |   "labeled entities": "[(3, 4, 'cp')]"
1929 |  },
1930 |  {
1931 |   "sentence": "['我', '要', '买', '寿', '司', '帘', '竹', '帘']",
1932 |   "labeled entities": "[(3, 5, 'cp'), (6, 7, 'cp')]"
1933 |  },
1934 |  {
1935 |   "sentence": "['我', '要', '买', '紫', '甘', '蓝']",
1936 |   "labeled entities": "[(3, 5, 'cp')]"
1937 |  },
1938 |  {
1939 |   "sentence": "['我', '要', '买', '宝', '宝', '花', '露', '水']",
1940 |   "labeled entities": "[(3, 7, 'cp')]"
1941 |  },
1942 |  {
1943 |   "sentence": "['乐', '事', '薯', '片', '7', '0', 'g', '多', '少', '钱']",
1944 |   "labeled entities": "[(0, 1, 'pp'), (2, 3, 'cp'), (4, 6, 'gg')]"
1945 |  },
1946 |  {
1947 |   "sentence": "['我', '要', '买', '奶', '粉', '罐']",
1948 |   "labeled entities": "[(3, 5, 'cp')]"
1949 |  },
1950 |  {
1951 |   "sentence": "['洗', '脸', '巾', '一', '次', '性', '多', '少', '钱']",
1952 |   "labeled entities": "[(0, 2, 'cp')]"
1953 |  },
1954 |  {
1955 |   "sentence": "['旺', '仔', ' ', '牛', '奶', '多', '少', '钱']",
1956 |   "labeled entities": "[(0, 1, 'pp'), (3, 4, 'cp')]"
1957 |  },
1958 |  {
1959 |   "sentence": "['洗', '鞋', '刷', '子', '多', '少', '钱']",
1960 |   "labeled entities": "[(2, 3, 'cp')]"
1961 |  },
1962 |  {
1963 |   "sentence": "['葡', '萄', '籽', '多', '少', '钱']",
1964 |   "labeled entities": "[(0, 2, 'cp')]"
1965 |  },
1966 |  {
1967 |   "sentence": "['我', '要', '买', '冰', '红', '茶', ' ', '柠', '檬', '味']",
1968 |   "labeled entities": "[(3, 5, 'cp')]"
1969 |  },
1970 |  {
1971 |   "sentence": "['我', '要', '买', '进', '口', '肠']",
1972 |   "labeled entities": "[(3, 5, 'cp')]"
1973 |  },
1974 |  {
1975 |   "sentence": "['v', 'i', 't', 'a', ' ', 'c', 'o', 'c', 'o', '椰', '子', '水', '多', '少', '钱']",
1976 |   "labeled entities": "[(0, 8, 'pp'), (9, 11, 'cp')]"
1977 |  },
1978 |  {
1979 |   "sentence": "['我', '要', '买', '恒', '都', '牛', '排']",
1980 |   "labeled entities": "[(3, 4, 'pp'), (5, 6, 'cp')]"
1981 |  },
1982 |  {
1983 |   "sentence": "['女', '童', '连', '衣', '裙']",
1984 |   "labeled entities": "[(2, 4, 'cp')]"
1985 |  },
1986 |  {
1987 |   "sentence": "['刀', '削', '面', '方', '便', '面', '多', '少', '钱']",
1988 |   "labeled entities": "[(0, 2, 'cp'), (3, 5, 'cp')]"
1989 |  },
1990 |  {
1991 |   "sentence": "['我', '要', '买', '米', '油']",
1992 |   "labeled entities": "[(3, 3, 'cp'), (4, 4, 'cp')]"
1993 |  },
1994 |  {
1995 |   "sentence": "['我', '要', '买', '西', '王', '油']",
1996 |   "labeled entities": "[(3, 4, 'pp'), (5, 5, 'cp')]"
1997 |  },
1998 |  {
1999 |   "sentence": "['婴', '儿', '一', '段', '奶', '粉', '多', '少', '钱']",
2000 |   "labeled entities": "[(4, 5, 'cp')]"
2001 |  },
2002 |  {
2003 |   "sentence": "['欧', '莱', '雅', '女', '士', '多', '少', '钱']",
2004 |   "labeled entities": "[(0, 2, 'pp')]"
2005 |  },
2006 |  {
2007 |   "sentence": "['u', 's', 'b', '数', '据', '线', '多', '少', '钱']",
2008 |   "labeled entities": "[(0, 5, 'cp')]"
2009 |  },
2010 |  {
2011 |   "sentence": "['学', '生', '奶', '多', '少', '钱']",
2012 |   "labeled entities": "[(0, 2, 'cp')]"
2013 |  },
2014 |  {
2015 |   "sentence": "['万', '字', '酱', '油', '多', '少', '钱']",
2016 |   "labeled entities": "[(0, 1, 'pp'), (2, 3, 'cp')]"
2017 |  },
2018 |  {
2019 |   "sentence": "['茶', '树', '菇', '多', '少', '钱']",
2020 |   "labeled entities": "[(0, 2, 'cp')]"
2021 |  },
2022 |  {
2023 |   "sentence": "['凉', '鞋', '女', '童']",
2024 |   "labeled entities": "[(0, 1, 'cp')]"
2025 |  },
2026 |  {
2027 |   "sentence": "['洗', '面', '奶']",
2028 |   "labeled entities": "[(0, 2, 'cp')]"
2029 |  },
2030 |  {
2031 |   "sentence": "['我', '要', '买', '贵', '州', '干', '辣', '椒']",
2032 |   "labeled entities": "[(5, 7, 'cp')]"
2033 |  },
2034 |  {
2035 |   "sentence": "['我', '要', '买', '丽', '丽', '贝', '尔', '化', '妆', '棉']",
2036 |   "labeled entities": "[(3, 6, 'pp'), (7, 9, 'cp')]"
2037 |  },
2038 |  {
2039 |   "sentence": "['公', '主', '裙']",
2040 |   "labeled entities": "[(0, 2, 'cp')]"
2041 |  },
2042 |  {
2043 |   "sentence": "['波', '士', '顿', '龙', '虾', '多', '少', '钱']",
2044 |   "labeled entities": "[(0, 4, 'cp')]"
2045 |  },
2046 |  {
2047 |   "sentence": "['我', '想', '要', '布', '鞋']",
2048 |   "labeled entities": "[(3, 4, 'cp')]"
2049 |  },
2050 |  {
2051 |   "sentence": "['燕', '塘', '甜', '牛', '奶', '多', '少', '钱']",
2052 |   "labeled entities": "[(0, 1, 'pp'), (2, 4, 'cp')]"
2053 |  },
2054 |  {
2055 |   "sentence": "['我', '要', '买', '阿', '迪', '达', '斯', '套', '装']",
2056 |   "labeled entities": "[(3, 6, 'pp'), (7, 8, 'cp')]"
2057 |  },
2058 |  {
2059 |   "sentence": "['桃', '片', '多', '少', '钱']",
2060 |   "labeled entities": "[(0, 1, 'cp')]"
2061 |  },
2062 |  {
2063 |   "sentence": "['我', '要', '买', '套', '套', ' ', '情', '趣', ' ', '男', '用', ' ', '安', '全', '套']",
2064 |   "labeled entities": "[(3, 4, 'cp'), (12, 14, 'cp')]"
2065 |  },
2066 |  {
2067 |   "sentence": "['妙', '妙', '多', '少', '钱']",
2068 |   "labeled entities": "[(0, 1, 'cp')]"
2069 |  },
2070 |  {
2071 |   "sentence": "['袋', '鼠', '红', '酒', '多', '少', '钱']",
2072 |   "labeled entities": "[(0, 1, 'pp'), (2, 3, 'cp')]"
2073 |  },
2074 |  {
2075 |   "sentence": "['买', '躺', '椅']",
2076 |   "labeled entities": "[(1, 2, 'cp')]"
2077 |  },
2078 |  {
2079 |   "sentence": "['老', '面', '包', '多', '少', '钱']",
2080 |   "labeled entities": "[(0, 2, 'cp')]"
2081 |  },
2082 |  {
2083 |   "sentence": "['西', '餐', '刀', '叉', '多', '少', '钱']",
2084 |   "labeled entities": "[(2, 3, 'cp')]"
2085 |  },
2086 |  {
2087 |   "sentence": "['外', '婆', '菜', '多', '少', '钱']",
2088 |   "labeled entities": "[(0, 2, 'cp')]"
2089 |  },
2090 |  {
2091 |   "sentence": "['烤', '鸡', '翅', '多', '少', '钱']",
2092 |   "labeled entities": "[(0, 2, 'cp')]"
2093 |  },
2094 |  {
2095 |   "sentence": "['好']",
2096 |   "labeled entities": "[]"
2097 |  },
2098 |  {
2099 |   "sentence": "['成', '人', '牙', '刷', '多', '少', '钱']",
2100 |   "labeled entities": "[(0, 3, 'cp')]"
2101 |  },
2102 |  {
2103 |   "sentence": "['隐', '形', '眼', '镜', '护', '理', '液', '多', '少', '钱']",
2104 |   "labeled entities": "[(0, 6, 'cp')]"
2105 |  },
2106 |  {
2107 |   "sentence": "['我', '要', '买', '驴', '肉']",
2108 |   "labeled entities": "[(3, 4, 'cp')]"
2109 |  },
2110 |  {
2111 |   "sentence": "['短', '裤']",
2112 |   "labeled entities": "[(0, 1, 'cp')]"
2113 |  },
2114 |  {
2115 |   "sentence": "['我', '要', '买', '油', '沾', '米']",
2116 |   "labeled entities": "[(3, 5, 'cp')]"
2117 |  },
2118 |  {
2119 |   "sentence": "['m', '巾', '多', '少', '钱']",
2120 |   "labeled entities": "[(0, 1, 'cp')]"
2121 |  },
2122 |  {
2123 |   "sentence": "['山', '核', '桃', '仁', '小', '包', '装', '多', '少', '钱']",
2124 |   "labeled entities": "[(0, 3, 'cp')]"
2125 |  },
2126 |  {
2127 |   "sentence": "['我', '要', '买', '鸿', '毛', '药', '酒']",
2128 |   "labeled entities": "[(3, 4, 'pp'), (5, 6, 'cp')]"
2129 |  },
2130 |  {
2131 |   "sentence": "['猪', '大', '排', '多', '少', '钱']",
2132 |   "labeled entities": "[(0, 2, 'cp')]"
2133 |  },
2134 |  {
2135 |   "sentence": "['麻', '烦', '说', '下', '牛', '奶', '最', '近', '降', '价', '没', '，', '好', '吗']",
2136 |   "labeled entities": "[(4, 5, 'cp')]"
2137 |  },
2138 |  {
2139 |   "sentence": "['干', '燥', '除', '湿', '多', '少', '钱']",
2140 |   "labeled entities": "[]"
2141 |  },
2142 |  {
2143 |   "sentence": "['我', '要', '买', '饭', '爷']",
2144 |   "labeled entities": "[(3, 4, 'pp')]"
2145 |  },
2146 |  {
2147 |   "sentence": "['我', '要', '买', '吸', '管']",
2148 |   "labeled entities": "[(3, 4, 'cp')]"
2149 |  },
2150 |  {
2151 |   "sentence": "['香', '肠', '整', '箱', '多', '少', '钱']",
2152 |   "labeled entities": "[(0, 1, 'cp'), (2, 3, 'gg')]"
2153 |  },
2154 |  {
2155 |   "sentence": "['洗', '头', '膏', '套', '装', '多', '少', '钱']",
2156 |   "labeled entities": "[(0, 4, 'cp')]"
2157 |  },
2158 |  {
2159 |   "sentence": "['我', '要', '买', '马', '桶', '除', '臭']",
2160 |   "labeled entities": "[(3, 6, 'cp')]"
2161 |  },
2162 |  {
2163 |   "sentence": "['我', '要', '买', '镜']",
2164 |   "labeled entities": "[(3, 3, 'cp')]"
2165 |  },
2166 |  {
2167 |   "sentence": "['我', '要', '买', '妙', '妙', '鱿', '鱼', '味', '卷']",
2168 |   "labeled entities": "[(3, 4, 'pp'), (5, 8, 'cp')]"
2169 |  },
2170 |  {
2171 |   "sentence": "['果', '粉', '多', '少', '钱']",
2172 |   "labeled entities": "[(0, 1, 'cp')]"
2173 |  },
2174 |  {
2175 |   "sentence": "['英', '雄']",
2176 |   "labeled entities": "[(0, 1, 'pp')]"
2177 |  },
2178 |  {
2179 |   "sentence": "['我', '要', '买', '4', '2', '寸', '的', '电', '视']",
2180 |   "labeled entities": "[(3, 5, 'gg'), (7, 8, 'cp')]"
2181 |  },
2182 |  {
2183 |   "sentence": "['我', '要', '买', '蘸', '酱']",
2184 |   "labeled entities": "[(3, 4, 'cp')]"
2185 |  },
2186 |  {
2187 |   "sentence": "['发', '胶', ' ', '喷', '雾', '多', '少', '钱']",
2188 |   "labeled entities": "[(0, 4, 'cp')]"
2189 |  },
2190 |  {
2191 |   "sentence": "['丝', '毛', '多', '少', '钱']",
2192 |   "labeled entities": "[(0, 1, 'cp')]"
2193 |  },
2194 |  {
2195 |   "sentence": "['我', '要', '买', '蓝', '牙', '耳', '机']",
2196 |   "labeled entities": "[(3, 6, 'cp')]"
2197 |  },
2198 |  {
2199 |   "sentence": "['我', '要', '买', '鲜', '鱿', '鱼']",
2200 |   "labeled entities": "[(3, 5, 'cp')]"
2201 |  },
2202 |  {
2203 |   "sentence": "['我', '要', '买', '雪', '花', '片', '积', '木']",
2204 |   "labeled entities": "[(3, 7, 'cp')]"
2205 |  },
2206 |  {
2207 |   "sentence": "['肤', '乐', '维', '肤', '霜', '多', '少', '钱']",
2208 |   "labeled entities": "[(0, 4, 'cp')]"
2209 |  },
2210 |  {
2211 |   "sentence": "['买', '气', '球']",
2212 |   "labeled entities": "[(1, 2, 'cp')]"
2213 |  },
2214 |  {
2215 |   "sentence": "['红', '富', '士', '多', '少', '钱']",
2216 |   "labeled entities": "[(0, 2, 'cp')]"
2217 |  },
2218 |  {
2219 |   "sentence": "['蒸', '蛋', '多', '少', '钱']",
2220 |   "labeled entities": "[(0, 1, 'cp')]"
2221 |  },
2222 |  {
2223 |   "sentence": "['我', '要', '买', '帮', '宝', '适', 'n', 'b']",
2224 |   "labeled entities": "[(3, 5, 'pp'), (6, 7, 'xh')]"
2225 |  },
2226 |  {
2227 |   "sentence": "['买', '抽', '纸']",
2228 |   "labeled entities": "[(1, 2, 'cp')]"
2229 |  },
2230 |  {
2231 |   "sentence": "['我', '要', '买', '黑', '人', '漱', '口', '水']",
2232 |   "labeled entities": "[(3, 4, 'pp'), (5, 7, 'cp')]"
2233 |  },
2234 |  {
2235 |   "sentence": "['我', '要', '买', '法', '兰', '琳', '卡', '面', '膜']",
2236 |   "labeled entities": "[(3, 6, 'pp'), (7, 8, 'cp')]"
2237 |  },
2238 |  {
2239 |   "sentence": "['我', '要', '买', '甘', '蔗']",
2240 |   "labeled entities": "[(3, 4, 'cp')]"
2241 |  },
2242 |  {
2243 |   "sentence": "['我', '要', '买', '花', '花', '公', '子']",
2244 |   "labeled entities": "[(3, 6, 'cp')]"
2245 |  },
2246 |  {
2247 |   "sentence": "['我', '要', '买', '拖', '把', '海', '绵', '替', '换', '头']",
2248 |   "labeled entities": "[(3, 4, 'cp'), (5, 9, 'cp')]"
2249 |  },
2250 |  {
2251 |   "sentence": "['可', '爱']",
2252 |   "labeled entities": "[]"
2253 |  },
2254 |  {
2255 |   "sentence": "['我', '要', '买', '爱', '他', '美', 'p', 'r', 'e']",
2256 |   "labeled entities": "[(3, 5, 'pp'), (6, 8, 'xh')]"
2257 |  },
2258 |  {
2259 |   "sentence": "['我', '要', '买', '加', '菲', '猫', '护', '肤', '品']",
2260 |   "labeled entities": "[(3, 5, 'pp'), (6, 8, 'cp')]"
2261 |  },
2262 |  {
2263 |   "sentence": "['我', '要', '买', '桂', '格', '燕', '麦', '饼', '干']",
2264 |   "labeled entities": "[(3, 4, 'pp'), (5, 6, 'yl'), (7, 8, 'cp')]"
2265 |  },
2266 |  {
2267 |   "sentence": "['插', '头', '多', '少', '钱']",
2268 |   "labeled entities": "[(0, 1, 'cp')]"
2269 |  },
2270 |  {
2271 |   "sentence": "['我', '要', '买', '山', '核', '桃', '瓜', '子']",
2272 |   "labeled entities": "[(3, 7, 'cp')]"
2273 |  },
2274 |  {
2275 |   "sentence": "['百', '草', '味', '鸭', '舌', '多', '少', '钱']",
2276 |   "labeled entities": "[(0, 2, 'pp'), (3, 4, 'cp')]"
2277 |  },
2278 |  {
2279 |   "sentence": "['卫', '生', '巾', '超', '长', '夜', '用', '多', '少', '钱']",
2280 |   "labeled entities": "[(0, 2, 'cp')]"
2281 |  },
2282 |  {
2283 |   "sentence": "['我', '要', '买', '脱', '脂', '牛', '奶', ' ', '1', 'l']",
2284 |   "labeled entities": "[(3, 6, 'cp'), (8, 9, 'gg')]"
2285 |  },
2286 |  {
2287 |   "sentence": "['我', '要', '买', '防', '蚊', '喷', '雾', ' ', '儿', '童']",
2288 |   "labeled entities": "[(3, 6, 'cp')]"
2289 |  },
2290 |  {
2291 |   "sentence": "['早', '餐', '冲', '饮', '谷', '物', '多', '少', '钱']",
2292 |   "labeled entities": "[(2, 5, 'cp')]"
2293 |  },
2294 |  {
2295 |   "sentence": "['九', '阳', '破', '壁', '机']",
2296 |   "labeled entities": "[(0, 1, 'pp'), (2, 4, 'cp')]"
2297 |  },
2298 |  {
2299 |   "sentence": "['烤', '多', '少', '钱']",
2300 |   "labeled entities": "[]"
2301 |  },
2302 |  {
2303 |   "sentence": "['红', '杏', '干', '多', '少', '钱']",
2304 |   "labeled entities": "[(0, 2, 'cp')]"
2305 |  },
2306 |  {
2307 |   "sentence": "['我', '要', '买', '农', '夫', '山', '泉', '水', '柠', '檬']",
2308 |   "labeled entities": "[(3, 6, 'pp'), (7, 9, 'cp')]"
2309 |  },
2310 |  {
2311 |   "sentence": "['手', '动', '剃', '须', '刀', '多', '少', '钱']",
2312 |   "labeled entities": "[(0, 4, 'cp')]"
2313 |  },
2314 |  {
2315 |   "sentence": "['儿', '童', '游', '泳', '圈', '多', '少', '钱']",
2316 |   "labeled entities": "[(2, 4, 'cp')]"
2317 |  },
2318 |  {
2319 |   "sentence": "['氧', '多', '少', '钱']",
2320 |   "labeled entities": "[]"
2321 |  },
2322 |  {
2323 |   "sentence": "['我', '要', '买', '刀', '削', '面', '削', '面', '刀']",
2324 |   "labeled entities": "[(6, 8, 'cp')]"
2325 |  },
2326 |  {
2327 |   "sentence": "['衣', '物', '除', '菌', '液', '多', '少', '钱']",
2328 |   "labeled entities": "[(0, 4, 'cp')]"
2329 |  },
2330 |  {
2331 |   "sentence": "['沐', '浴', '露', '女', '多', '少', '钱']",
2332 |   "labeled entities": "[(0, 2, 'cp')]"
2333 |  },
2334 |  {
2335 |   "sentence": "['我', '要', '买', '食', '品', '收', '纳', '盒']",
2336 |   "labeled entities": "[(3, 7, 'cp')]"
2337 |  },
2338 |  {
2339 |   "sentence": "['我', '要', '买', '阿', '舍', '食', '堂']",
2340 |   "labeled entities": "[(3, 6, 'pp')]"
2341 |  },
2342 |  {
2343 |   "sentence": "['学', '生', '奶', '粉', '多', '少', '钱']",
2344 |   "labeled entities": "[(0, 3, 'cp')]"
2345 |  },
2346 |  {
2347 |   "sentence": "['冰', '糖', '雪', '梨', '多', '少', '钱']",
2348 |   "labeled entities": "[(0, 3, 'cp')]"
2349 |  },
2350 |  {
2351 |   "sentence": "['盆', '子', '多', '少', '钱']",
2352 |   "labeled entities": "[(0, 1, 'cp')]"
2353 |  },
2354 |  {
2355 |   "sentence": "['我', '要', '买', '泰', '国', '香', '米', '茉', '莉', '香', '米', ' ', '原', '装', '进', '口', '大', '米']",
2356 |   "labeled entities": "[(5, 6, 'cp'), (9, 10, 'cp'), (16, 17, 'cp')]"
2357 |  },
2358 |  {
2359 |   "sentence": "['香', '水', '沐', '浴', '露', '多', '少', '钱']",
2360 |   "labeled entities": "[(0, 4, 'cp')]"
2361 |  },
2362 |  {
2363 |   "sentence": "['闷', '烧', '杯', '多', '少', '钱']",
2364 |   "labeled entities": "[(0, 2, 'cp')]"
2365 |  },
2366 |  {
2367 |   "sentence": "['我', '要', '买', '玉', '米', '热', '狗', '肠']",
2368 |   "labeled entities": "[(3, 7, 'cp')]"
2369 |  },
2370 |  {
2371 |   "sentence": "['我', '要', '买', '笋', '干', '即', '食']",
2372 |   "labeled entities": "[(3, 4, 'cp')]"
2373 |  },
2374 |  {
2375 |   "sentence": "['韩', '国', '进', '口', '饮', '料', '多', '少', '钱']",
2376 |   "labeled entities": "[(4, 5, 'cp')]"
2377 |  },
2378 |  {
2379 |   "sentence": "['唇', '膏']",
2380 |   "labeled entities": "[(0, 1, 'cp')]"
2381 |  },
2382 |  {
2383 |   "sentence": "['我', '想', '买', '安', '眠', '药']",
2384 |   "labeled entities": "[(3, 5, 'cp')]"
2385 |  },
2386 |  {
2387 |   "sentence": "['我', '要', '买', '小', '白', '熊', '奶', '瓶', '消', '毒', '器']",
2388 |   "labeled entities": "[(3, 5, 'pp'), (6, 10, 'cp')]"
2389 |  },
2390 |  {
2391 |   "sentence": "['我', '要', '买', '生', '花', '生', '米', ' ', '花', '生', '仁']",
2392 |   "labeled entities": "[(3, 6, 'cp'), (8, 10, 'cp')]"
2393 |  },
2394 |  {
2395 |   "sentence": "['雀', '巢', '能', '恩', '3', '段', '多', '少', '钱']",
2396 |   "labeled entities": "[(0, 1, 'pp'), (2, 3, 'xh')]"
2397 |  },
2398 |  {
2399 |   "sentence": "['家', '具', '安', '装']",
2400 |   "labeled entities": "[]"
2401 |  },
2402 |  {
2403 |   "sentence": "['爱', '得', '利', '奶', '嘴', '多', '少', '钱']",
2404 |   "labeled entities": "[(0, 2, 'pp'), (3, 4, 'cp')]"
2405 |  },
2406 |  {
2407 |   "sentence": "['短', '款', '的']",
2408 |   "labeled entities": "[]"
2409 |  },
2410 |  {
2411 |   "sentence": "['我', '要', '买', '微', '波', '炉', '饭', '盒']",
2412 |   "labeled entities": "[(3, 7, 'cp')]"
2413 |  },
2414 |  {
2415 |   "sentence": "['减', '肥']",
2416 |   "labeled entities": "[]"
2417 |  },
2418 |  {
2419 |   "sentence": "['香', '水', ' ', '女', '士', '多', '少', '钱']",
2420 |   "labeled entities": "[(0, 1, 'cp')]"
2421 |  },
2422 |  {
2423 |   "sentence": "['o', 'p', 'p', 'o', 'A', '7', 'p', 'l', 'u', 's']",
2424 |   "labeled entities": "[(0, 3, 'pp'), (4, 9, 'xh')]"
2425 |  },
2426 |  {
2427 |   "sentence": "['我', '要', '买', '厨', '房', '调', '料', '盒']",
2428 |   "labeled entities": "[(5, 7, 'cp')]"
2429 |  },
2430 |  {
2431 |   "sentence": "['麦', '饭', '石', '煎', '锅', '多', '少', '钱']",
2432 |   "labeled entities": "[(0, 2, 'yl'), (3, 4, 'cp')]"
2433 |  },
2434 |  {
2435 |   "sentence": "['波', '力', '海', '苔', '卷', '多', '少', '钱']",
2436 |   "labeled entities": "[(0, 1, 'pp'), (2, 4, 'cp')]"
2437 |  },
2438 |  {
2439 |   "sentence": "['我', '要', '买', '妙', '洁', ' ', '百', '洁', '布']",
2440 |   "labeled entities": "[(3, 4, 'pp'), (6, 8, 'cp')]"
2441 |  },
2442 |  {
2443 |   "sentence": "['茉', '莉', '花', '茶']",
2444 |   "labeled entities": "[(0, 3, 'cp')]"
2445 |  },
2446 |  {
2447 |   "sentence": "['凯', '儿', '得', '乐', '纸', '尿', '裤', '多', '少', '钱']",
2448 |   "labeled entities": "[(0, 3, 'pp'), (4, 6, 'cp')]"
2449 |  },
2450 |  {
2451 |   "sentence": "['挂', '钩', ' ', '吸', '盘', '多', '少', '钱']",
2452 |   "labeled entities": "[(0, 1, 'cp'), (3, 4, 'cp')]"
2453 |  },
2454 |  {
2455 |   "sentence": "['我', '要', '买', '冬', '虫', '夏', '草']",
2456 |   "labeled entities": "[(3, 6, 'cp')]"
2457 |  },
2458 |  {
2459 |   "sentence": "['定', '制']",
2460 |   "labeled entities": "[]"
2461 |  },
2462 |  {
2463 |   "sentence": "['青', '岛', '纯', '生', '啤', '酒', '5', '0', '0', 'm', 'l', '多', '少', '钱']",
2464 |   "labeled entities": "[(0, 1, 'pp'), (4, 5, 'cp'), (6, 10, 'gg')]"
2465 |  },
2466 |  {
2467 |   "sentence": "['锅', '刷', '多', '少', '钱']",
2468 |   "labeled entities": "[(0, 1, 'cp')]"
2469 |  },
2470 |  {
2471 |   "sentence": "['我', '要', '买', '小', '紫', '薯']",
2472 |   "labeled entities": "[(4, 5, 'cp')]"
2473 |  },
2474 |  {
2475 |   "sentence": "['蒸', '鱼', '酱', '油', '多', '少', '钱']",
2476 |   "labeled entities": "[(0, 3, 'cp')]"
2477 |  },
2478 |  {
2479 |   "sentence": "['背', '带', '裙']",
2480 |   "labeled entities": "[(0, 2, 'cp')]"
2481 |  },
2482 |  {
2483 |   "sentence": "['果', '干', '蜜', '饯', '多', '少', '钱']",
2484 |   "labeled entities": "[(0, 1, 'cp'), (2, 3, 'cp')]"
2485 |  },
2486 |  {
2487 |   "sentence": "['电', '池', '炉', '多', '少', '钱']",
2488 |   "labeled entities": "[(0, 2, 'cp')]"
2489 |  },
2490 |  {
2491 |   "sentence": "['我', '要', '买', '满', '婷', '沐', '浴', '露']",
2492 |   "labeled entities": "[(3, 4, 'pp'), (5, 7, 'cp')]"
2493 |  },
2494 |  {
2495 |   "sentence": "['洗', '面', '奶', ' ', '女', '多', '少', '钱']",
2496 |   "labeled entities": "[(0, 2, 'cp')]"
2497 |  },
2498 |  {
2499 |   "sentence": "['我', '要', '买', '欧', '德', '堡', '全', '脂', '纯', '牛', '奶']",
2500 |   "labeled entities": "[(3, 5, 'pp'), (6, 10, 'cp')]"
2501 |  },
2502 |  {
2503 |   "sentence": "['我', '要', '买', '海', '天', '拌', '饭', '酱']",
2504 |   "labeled entities": "[(3, 4, 'pp'), (5, 7, 'cp')]"
2505 |  },
2506 |  {
2507 |   "sentence": "['我', '要', '买', '麦', '片', '早', '餐']",
2508 |   "labeled entities": "[(3, 4, 'cp')]"
2509 |  },
2510 |  {
2511 |   "sentence": "['我', '要', '买', '果', '浦']",
2512 |   "labeled entities": "[(3, 4, 'cp')]"
2513 |  },
2514 |  {
2515 |   "sentence": "['我', '要', '买', '卫', '生', '纸', '实', '心']",
2516 |   "labeled entities": "[(3, 5, 'cp')]"
2517 |  },
2518 |  {
2519 |   "sentence": "['买', '二', '免', '一', '牙', '膏', '多', '少', '钱']",
2520 |   "labeled entities": "[(4, 5, 'cp')]"
2521 |  },
2522 |  {
2523 |   "sentence": "['我', '要', '买', '儿', '童', '保', '温', '杯']",
2524 |   "labeled entities": "[(5, 7, 'cp')]"
2525 |  },
2526 |  {
2527 |   "sentence": "['湿', '纸', '巾', ' ', '婴', '儿', '多', '少', '钱']",
2528 |   "labeled entities": "[(0, 2, 'cp')]"
2529 |  },
2530 |  {
2531 |   "sentence": "['我', '要', '买', '婴', '儿', '衣', '服']",
2532 |   "labeled entities": "[(3, 6, 'cp')]"
2533 |  },
2534 |  {
2535 |   "sentence": "['我', '要', '买', '橙', '汁', '浓', '缩']",
2536 |   "labeled entities": "[(3, 4, 'cp')]"
2537 |  },
2538 |  {
2539 |   "sentence": "['我', '要', '买', '耐', '克']",
2540 |   "labeled entities": "[(3, 4, 'pp')]"
2541 |  },
2542 |  {
2543 |   "sentence": "['抽', '纸', '整', '箱', '2', '4', '包', '多', '少', '钱']",
2544 |   "labeled entities": "[(0, 1, 'cp'), (4, 6, 'gg')]"
2545 |  },
2546 |  {
2547 |   "sentence": "['肥', '皂', '内', '衣', '专', '用', '多', '少', '钱']",
2548 |   "labeled entities": "[(0, 1, 'cp')]"
2549 |  },
2550 |  {
2551 |   "sentence": "['我', '要', '买', '榛', '子', '坚', '果']",
2552 |   "labeled entities": "[(3, 4, 'cp'), (5, 6, 'cp')]"
2553 |  },
2554 |  {
2555 |   "sentence": "['蓝', '月', '亮', '洁', '厕', '液', '多', '少', '钱']",
2556 |   "labeled entities": "[(0, 2, 'pp'), (3, 5, 'cp')]"
2557 |  },
2558 |  {
2559 |   "sentence": "['我', '要', '买', '水', '果', '糖', ' ', '混', '合', '水', '果', '味', '进', '口']",
2560 |   "labeled entities": "[(3, 5, 'cp')]"
2561 |  },
2562 |  {
2563 |   "sentence": "['我', '要', '买', '保', '温', '桶', '3', '0', '4', '不', '锈', '钢']",
2564 |   "labeled entities": "[(3, 5, 'cp'), (6, 11, 'yl')]"
2565 |  },
2566 |  {
2567 |   "sentence": "['我', '要', '买', '保', '温', '碗']",
2568 |   "labeled entities": "[(3, 5, 'cp')]"
2569 |  },
2570 |  {
2571 |   "sentence": "['我', '要', '买', 'v', 's', '沙', '宣', '洗', '发', '水']",
2572 |   "labeled entities": "[(3, 4, 'pp'), (5, 6, 'pp'), (7, 9, 'cp')]"
2573 |  },
2574 |  {
2575 |   "sentence": "['我', '要', '买', '耶', '汁']",
2576 |   "labeled entities": "[(3, 4, 'cp')]"
2577 |  },
2578 |  {
2579 |   "sentence": "['我', '要', '买', '爽', '身', '粉', '宝', '宝', '痱', '子', '粉']",
2580 |   "labeled entities": "[(3, 5, 'cp'), (8, 10, 'cp')]"
2581 |  },
2582 |  {
2583 |   "sentence": "['我', '要', '买', '被', '罩']",
2584 |   "labeled entities": "[(3, 4, 'cp')]"
2585 |  },
2586 |  {
2587 |   "sentence": "['隆', '力', '奇', '沐', '浴', '露', '多', '少', '钱']",
2588 |   "labeled entities": "[(0, 2, 'pp'), (3, 5, 'cp')]"
2589 |  },
2590 |  {
2591 |   "sentence": "['华', '为', 'p', '9', '多', '少', '钱']",
2592 |   "labeled entities": "[(0, 1, 'pp'), (2, 3, 'xh')]"
2593 |  },
2594 |  {
2595 |   "sentence": "['我', '要', '买', '辣', '椒', '油', ' ', '瓶']",
2596 |   "labeled entities": "[(3, 5, 'cp'), (7, 7, 'gg')]"
2597 |  },
2598 |  {
2599 |   "sentence": "['我', '要', '买', '辣', '豆', '腐']",
2600 |   "labeled entities": "[(3, 5, 'cp')]"
2601 |  },
2602 |  {
2603 |   "sentence": "['我', '要', '买', '浴', '室', '防', '滑', '垫']",
2604 |   "labeled entities": "[(3, 7, 'cp')]"
2605 |  },
2606 |  {
2607 |   "sentence": "['我', '要', '买', '黑', '糖', '麻', '花']",
2608 |   "labeled entities": "[(3, 6, 'cp')]"
2609 |  },
2610 |  {
2611 |   "sentence": "['儿', '童', ' ', '毛', '巾', '多', '少', '钱']",
2612 |   "labeled entities": "[(3, 4, 'cp')]"
2613 |  },
2614 |  {
2615 |   "sentence": "['伴', '面', '多', '少', '钱']",
2616 |   "labeled entities": "[(0, 1, 'cp')]"
2617 |  },
2618 |  {
2619 |   "sentence": "['我', '要', '买', '海', '马']",
2620 |   "labeled entities": "[(3, 4, 'cp')]"
2621 |  },
2622 |  {
2623 |   "sentence": "['我', '要', '买', '长', '鼻', '王']",
2624 |   "labeled entities": "[(3, 5, 'pp')]"
2625 |  },
2626 |  {
2627 |   "sentence": "['红', '豆', '薏', '米', '粉']",
2628 |   "labeled entities": "[(0, 4, 'cp')]"
2629 |  },
2630 |  {
2631 |   "sentence": "['花', '洒']",
2632 |   "labeled entities": "[(0, 1, 'cp')]"
2633 |  },
2634 |  {
2635 |   "sentence": "['好', '孩', '子', '奶', '嘴', '多', '少', '钱']",
2636 |   "labeled entities": "[(0, 2, 'pp'), (3, 4, 'cp')]"
2637 |  },
2638 |  {
2639 |   "sentence": "['春', '雨']",
2640 |   "labeled entities": "[(0, 1, 'pp')]"
2641 |  },
2642 |  {
2643 |   "sentence": "['电', '磁', '炉', '多', '少', '钱']",
2644 |   "labeled entities": "[(0, 2, 'cp')]"
2645 |  },
2646 |  {
2647 |   "sentence": "['大', '益', '普', '洱', '茶', '多', '少', '钱']",
2648 |   "labeled entities": "[(0, 1, 'pp'), (2, 4, 'cp')]"
2649 |  },
2650 |  {
2651 |   "sentence": "['我', '要', '买', '滋', '源', '无', '硅', '油']",
2652 |   "labeled entities": "[(3, 4, 'pp')]"
2653 |  },
2654 |  {
2655 |   "sentence": "['悠', '哈', '奶', '糖', '多', '少', '钱']",
2656 |   "labeled entities": "[(0, 1, 'pp'), (2, 3, 'cp')]"
2657 |  },
2658 |  {
2659 |   "sentence": "['我', '要', '买', '牛', '仔', '裤', '男']",
2660 |   "labeled entities": "[(3, 5, 'cp')]"
2661 |  },
2662 |  {
2663 |   "sentence": "['我', '要', '买', '调', '味', '汁']",
2664 |   "labeled entities": "[(3, 5, 'cp')]"
2665 |  },
2666 |  {
2667 |   "sentence": "['柴', '火', '大', '院', ' ', '五', '常', '稻', '花', '香', '米', '多', '少', '钱']",
2668 |   "labeled entities": "[(0, 3, 'pp'), (7, 10, 'cp')]"
2669 |  },
2670 |  {
2671 |   "sentence": "['银', '项', '链', '多', '少', '钱']",
2672 |   "labeled entities": "[(0, 0, 'yl'), (1, 2, 'cp')]"
2673 |  },
2674 |  {
2675 |   "sentence": "['我', '要', '买', '炒', '面', '大', '王']",
2676 |   "labeled entities": "[(3, 6, 'cp')]"
2677 |  },
2678 |  {
2679 |   "sentence": "['浴', '巾', ' ', '纯', '棉', '多', '少', '钱']",
2680 |   "labeled entities": "[(0, 1, 'cp'), (3, 4, 'yl')]"
2681 |  },
2682 |  {
2683 |   "sentence": "['我', '要', '买', '辣']",
2684 |   "labeled entities": "[]"
2685 |  },
2686 |  {
2687 |   "sentence": "['蜘', '蛛', '王', '女', '鞋']",
2688 |   "labeled entities": "[(0, 2, 'pp'), (3, 4, 'cp')]"
2689 |  },
2690 |  {
2691 |   "sentence": "['买', '台', '式', '机', '固', '态', '硬', '盘']",
2692 |   "labeled entities": "[(4, 7, 'cp')]"
2693 |  },
2694 |  {
2695 |   "sentence": "['我', '要', '买', '新', '生', '儿', '衣', '服']",
2696 |   "labeled entities": "[(3, 7, 'cp')]"
2697 |  },
2698 |  {
2699 |   "sentence": "['我', '要', '买', '无', '糖', '苏', '打', '饼', '干']",
2700 |   "labeled entities": "[(5, 8, 'cp')]"
2701 |  },
2702 |  {
2703 |   "sentence": "['我', '要', '买', '笼', '屉']",
2704 |   "labeled entities": "[(3, 4, 'cp')]"
2705 |  },
2706 |  {
2707 |   "sentence": "['充', '电', '器', '苹', '果', '多', '少', '钱']",
2708 |   "labeled entities": "[(0, 2, 'cp'), (3, 4, 'pp')]"
2709 |  },
2710 |  {
2711 |   "sentence": "['伊', '利', '雪', '糕', '多', '少', '钱']",
2712 |   "labeled entities": "[(0, 1, 'pp'), (2, 3, 'cp')]"
2713 |  },
2714 |  {
2715 |   "sentence": "['我', '要', '买', '满', '9', '9', '减', '5', '0', '零', '食']",
2716 |   "labeled entities": "[(9, 10, 'cp')]"
2717 |  },
2718 |  {
2719 |   "sentence": "['我', '要', '买', '模', '具']",
2720 |   "labeled entities": "[(3, 4, 'cp')]"
2721 |  },
2722 |  {
2723 |   "sentence": "['婴', '儿', '纸', '巾', '多', '少', '钱']",
2724 |   "labeled entities": "[(0, 3, 'cp')]"
2725 |  },
2726 |  {
2727 |   "sentence": "['我', '要', '买', '龙', '井', '茶']",
2728 |   "labeled entities": "[(3, 5, 'cp')]"
2729 |  },
2730 |  {
2731 |   "sentence": "['我', '要', '买', '特', '步']",
2732 |   "labeled entities": "[(3, 4, 'pp')]"
2733 |  },
2734 |  {
2735 |   "sentence": "['韩', '国', '烤', '肉', '酱', '多', '少', '钱']",
2736 |   "labeled entities": "[(0, 4, 'cp')]"
2737 |  },
2738 |  {
2739 |   "sentence": "['家', '具', '美', '容']",
2740 |   "labeled entities": "[(0, 1, 'cp')]"
2741 |  },
2742 |  {
2743 |   "sentence": "['雪', '莲', '果', '多', '少', '钱']",
2744 |   "labeled entities": "[(0, 2, 'cp')]"
2745 |  },
2746 |  {
2747 |   "sentence": "['我', '要', '买', 'm', 'a', 'm', 'a']",
2748 |   "labeled entities": "[]"
2749 |  },
2750 |  {
2751 |   "sentence": "['木', '糖', '醇', '多', '少', '钱']",
2752 |   "labeled entities": "[(0, 2, 'cp')]"
2753 |  },
2754 |  {
2755 |   "sentence": "['七', '号', '南', '孚', '电', '池', '多', '少', '钱']",
2756 |   "labeled entities": "[(0, 1, 'gg'), (2, 3, 'pp'), (4, 5, 'cp')]"
2757 |  },
2758 |  {
2759 |   "sentence": "['卫', '生', '纸', '清', '风', '多', '少', '钱']",
2760 |   "labeled entities": "[(0, 2, 'cp'), (3, 4, 'pp')]"
2761 |  },
2762 |  {
2763 |   "sentence": "['新', '疆', '红', '枣', '多', '少', '钱']",
2764 |   "labeled entities": "[(2, 3, 'cp')]"
2765 |  },
2766 |  {
2767 |   "sentence": "['我', '要', '买', '怡', '口', '莲', '太', '妃', '糖']",
2768 |   "labeled entities": "[(3, 5, 'pp'), (6, 8, 'cp')]"
2769 |  },
2770 |  {
2771 |   "sentence": "['养', '胃', '多', '少', '钱']",
2772 |   "labeled entities": "[]"
2773 |  },
2774 |  {
2775 |   "sentence": "['想', '买', '点', '保', '健', '品']",
2776 |   "labeled entities": "[(3, 5, 'cp')]"
2777 |  },
2778 |  {
2779 |   "sentence": "['吉', '他', '多', '少', '钱']",
2780 |   "labeled entities": "[(0, 1, 'cp')]"
2781 |  },
2782 |  {
2783 |   "sentence": "['我', '要', '买', '竹', '叶', '青', '酒']",
2784 |   "labeled entities": "[(3, 6, 'cp')]"
2785 |  },
2786 |  {
2787 |   "sentence": "['防', '辐', '射', '眼', '镜']",
2788 |   "labeled entities": "[(0, 4, 'cp')]"
2789 |  },
2790 |  {
2791 |   "sentence": "['我', '要', '买', '儿', '童', '滑', '板', '车']",
2792 |   "labeled entities": "[(5, 7, 'cp')]"
2793 |  },
2794 |  {
2795 |   "sentence": "['我', '要', '买', '凝', '胶']",
2796 |   "labeled entities": "[(3, 4, 'cp')]"
2797 |  },
2798 |  {
2799 |   "sentence": "['深', '层', '清', '洁']",
2800 |   "labeled entities": "[]"
2801 |  },
2802 |  {
2803 |   "sentence": "['我', '要', '买', '辣', '片', ' ', '零', '食']",
2804 |   "labeled entities": "[(3, 4, 'cp'), (6, 7, 'cp')]"
2805 |  },
2806 |  {
2807 |   "sentence": "['盒', '纸', '多', '少', '钱']",
2808 |   "labeled entities": "[(0, 1, 'cp')]"
2809 |  },
2810 |  {
2811 |   "sentence": "['我', '要', '买', '补', '水', '面', '膜', ' ', '补', '水', '保', '湿']",
2812 |   "labeled entities": "[(5, 6, 'cp')]"
2813 |  },
2814 |  {
2815 |   "sentence": "['薇', '儿', '卫', '生', '巾', '多', '少', '钱']",
2816 |   "labeled entities": "[(0, 1, 'pp'), (2, 4, 'cp')]"
2817 |  },
2818 |  {
2819 |   "sentence": "['我', '要', '买', '腊', '肠']",
2820 |   "labeled entities": "[(3, 4, 'cp')]"
2821 |  },
2822 |  {
2823 |   "sentence": "['橘', '子', '工', '坊', '多', '少', '钱']",
2824 |   "labeled entities": "[(0, 3, 'pp')]"
2825 |  },
2826 |  {
2827 |   "sentence": "['豆', '浆', '粉', ' ', '冲', '饮', '多', '少', '钱']",
2828 |   "labeled entities": "[(0, 2, 'cp')]"
2829 |  },
2830 |  {
2831 |   "sentence": "['毛', '毯', '盖', '毯', '多', '少', '钱']",
2832 |   "labeled entities": "[(0, 1, 'cp'), (2, 3, 'cp')]"
2833 |  },
2834 |  {
2835 |   "sentence": "['浴', '室', '垫', '多', '少', '钱']",
2836 |   "labeled entities": "[(0, 2, 'cp')]"
2837 |  },
2838 |  {
2839 |   "sentence": "['光', '明', '莫', '斯', '利', '安', '酸', '奶', '多', '少', '钱']",
2840 |   "labeled entities": "[(0, 1, 'pp'), (2, 5, 'xh'), (6, 7, 'cp')]"
2841 |  },
2842 |  {
2843 |   "sentence": "['我', '要', '买', '隔', '离', '霜', '妆', '前', '乳']",
2844 |   "labeled entities": "[(3, 5, 'cp'), (6, 8, 'cp')]"
2845 |  },
2846 |  {
2847 |   "sentence": "['我', '要', '买', '今', '之', '逸', '品']",
2848 |   "labeled entities": "[(3, 6, 'pp')]"
2849 |  },
2850 |  {
2851 |   "sentence": "['我', '要', '买', '拖', '鞋', ' ', '男']",
2852 |   "labeled entities": "[(3, 4, 'cp')]"
2853 |  },
2854 |  {
2855 |   "sentence": "['植', '物', '医', '生', '多', '少', '钱']",
2856 |   "labeled entities": "[(0, 3, 'pp')]"
2857 |  },
2858 |  {
2859 |   "sentence": "['洗', '发', '水', ' ', '控', '油', '多', '少', '钱']",
2860 |   "labeled entities": "[(0, 2, 'cp')]"
2861 |  },
2862 |  {
2863 |   "sentence": "['我', '要', '买', '伞', ' ', '折', '叠']",
2864 |   "labeled entities": "[(3, 3, 'cp')]"
2865 |  },
2866 |  {
2867 |   "sentence": "['土', '豆', '饼', '多', '少', '钱']",
2868 |   "labeled entities": "[(0, 2, 'cp')]"
2869 |  },
2870 |  {
2871 |   "sentence": "['猕', '猴', '桃', '多', '少', '钱']",
2872 |   "labeled entities": "[(0, 2, 'cp')]"
2873 |  },
2874 |  {
2875 |   "sentence": "['收', '缩', '毛', '孔']",
2876 |   "labeled entities": "[]"
2877 |  },
2878 |  {
2879 |   "sentence": "['我', '要', '买', '儿', '童', '牙', '杯']",
2880 |   "labeled entities": "[(5, 6, 'cp')]"
2881 |  },
2882 |  {
2883 |   "sentence": "['清', '风', ' ', '卷', '纸', '多', '少', '钱']",
2884 |   "labeled entities": "[(0, 1, 'pp'), (3, 4, 'cp')]"
2885 |  },
2886 |  {
2887 |   "sentence": "['我', '要', '买', '糯', '米', '粉']",
2888 |   "labeled entities": "[(3, 5, 'cp')]"
2889 |  },
2890 |  {
2891 |   "sentence": "['咖', '啡', '饮', '料', '多', '少', '钱']",
2892 |   "labeled entities": "[(0, 3, 'cp')]"
2893 |  },
2894 |  {
2895 |   "sentence": "['我', '要', '买', '潘', '婷', '护', '发', '素', '乳', '液', '修', '护', '7', '5', '0', 'm', 'l']",
2896 |   "labeled entities": "[(3, 4, 'pp'), (5, 7, 'cp'), (12, 16, 'gg')]"
2897 |  },
2898 |  {
2899 |   "sentence": "['早', '晚', '牙', '膏', '多', '少', '钱']",
2900 |   "labeled entities": "[(0, 1, 'pp'), (2, 3, 'cp')]"
2901 |  },
2902 |  {
2903 |   "sentence": "['丁', '香', '茶', '多', '少', '钱']",
2904 |   "labeled entities": "[(0, 2, 'cp')]"
2905 |  },
2906 |  {
2907 |   "sentence": "['手', '机', 'm', 'a', 't', 'e', '9']",
2908 |   "labeled entities": "[(0, 1, 'cp'), (2, 6, 'xh')]"
2909 |  },
2910 |  {
2911 |   "sentence": "['我', '要', '买', '一', '次', '性', '内', '裤', ' ', '孕', '妇', '产', '妇', '产', '后', '月', '子', '用', '品']",
2912 |   "labeled entities": "[(3, 7, 'cp')]"
2913 |  },
2914 |  {
2915 |   "sentence": "['我', '要', '买', '蜀', '道', '香', '牛', '肉', '干']",
2916 |   "labeled entities": "[(3, 5, 'pp'), (6, 8, 'cp')]"
2917 |  },
2918 |  {
2919 |   "sentence": "['我', '要', '买', '潘', '婷', '洗', '发', '水', '4', '0', '0', 'm', 'l']",
2920 |   "labeled entities": "[(3, 4, 'pp'), (5, 7, 'cp'), (8, 12, 'gg')]"
2921 |  },
2922 |  {
2923 |   "sentence": "['拉', '芳', '多', '少', '钱']",
2924 |   "labeled entities": "[(0, 1, 'pp')]"
2925 |  },
2926 |  {
2927 |   "sentence": "['我', '要', '买', '辣', '妹', '子']",
2928 |   "labeled entities": "[(3, 5, 'pp')]"
2929 |  },
2930 |  {
2931 |   "sentence": "['花', '花', '公', '子', '多', '少', '钱']",
2932 |   "labeled entities": "[(0, 3, 'pp')]"
2933 |  },
2934 |  {
2935 |   "sentence": "['我', '要', '买', '提']",
2936 |   "labeled entities": "[]"
2937 |  },
2938 |  {
2939 |   "sentence": "['水', '晶', '之', '恋', '多', '少', '钱']",
2940 |   "labeled entities": "[(0, 3, 'cp')]"
2941 |  },
2942 |  {
2943 |   "sentence": "['馒', '头', '干', ' ', '烤', '馍', '片', '多', '少', '钱']",
2944 |   "labeled entities": "[(0, 2, 'cp'), (4, 6, 'cp')]"
2945 |  },
2946 |  {
2947 |   "sentence": "['我', '要', '买', '双', '鱼', '米', '醋']",
2948 |   "labeled entities": "[(3, 4, 'pp'), (5, 6, 'cp')]"
2949 |  },
2950 |  {
2951 |   "sentence": "['科', '罗', '纳', '多', '少', '钱']",
2952 |   "labeled entities": "[(0, 2, 'pp')]"
2953 |  },
2954 |  {
2955 |   "sentence": "['乐', '百', '氏', '多', '少', '钱']",
2956 |   "labeled entities": "[(0, 2, 'pp')]"
2957 |  },
2958 |  {
2959 |   "sentence": "['迷', '你', '榨', '汁', '机', '多', '少', '钱']",
2960 |   "labeled entities": "[(2, 4, 'cp')]"
2961 |  },
2962 |  {
2963 |   "sentence": "['男', '士', '袜', '子', '多', '少', '钱']",
2964 |   "labeled entities": "[(0, 3, 'cp')]"
2965 |  },
2966 |  {
2967 |   "sentence": "['辣', '翻', '天', '多', '少', '钱']",
2968 |   "labeled entities": "[(0, 2, 'pp')]"
2969 |  },
2970 |  {
2971 |   "sentence": "['空', '调', '风', '扇', '多', '少', '钱']",
2972 |   "labeled entities": "[(0, 3, 'cp')]"
2973 |  },
2974 |  {
2975 |   "sentence": "['我', '要', '买', '糖', '果', '袋']",
2976 |   "labeled entities": "[(3, 5, 'cp')]"
2977 |  },
2978 |  {
2979 |   "sentence": "['磨', '牙', '饼', '干', '6', '个', '月', '多', '少', '钱']",
2980 |   "labeled entities": "[(0, 3, 'cp')]"
2981 |  },
2982 |  {
2983 |   "sentence": "['毛', '巾', '纯', '棉', ' ', '洗', '脸', '儿', '童', '多', '少', '钱']",
2984 |   "labeled entities": "[(0, 1, 'cp'), (2, 3, 'yl')]"
2985 |  },
2986 |  {
2987 |   "sentence": "['我', '要', '买', '藤', '席', '凉', '席', '三', '件', '套']",
2988 |   "labeled entities": "[(3, 4, 'cp'), (5, 6, 'cp'), (7, 9, 'cp')]"
2989 |  },
2990 |  {
2991 |   "sentence": "['我', '要', '买', '美', '加', '净', '洗', '面', '奶']",
2992 |   "labeled entities": "[(3, 5, 'pp'), (6, 8, 'cp')]"
2993 |  },
2994 |  {
2995 |   "sentence": "['纯', '真', '酸', '奶', '多', '少', '钱']",
2996 |   "labeled entities": "[(0, 1, 'pp'), (2, 3, 'cp')]"
2997 |  },
2998 |  {
2999 |   "sentence": "['我', '要', '买', '金', '莲']",
3000 |   "labeled entities": "[(3, 4, 'cp')]"
3001 |  },
3002 |  {
3003 |   "sentence": "['甘', '竹', '多', '少', '钱']",
3004 |   "labeled entities": "[(0, 1, 'cp')]"
3005 |  },
3006 |  {
3007 |   "sentence": "['我', '要', '买', '鲜', '羊', '奶']",
3008 |   "labeled entities": "[(3, 5, 'cp')]"
3009 |  },
3010 |  {
3011 |   "sentence": "['我', '要', '买', '小', '镜', '子', ' ', '迷', '你']",
3012 |   "labeled entities": "[(4, 5, 'cp')]"
3013 |  },
3014 |  {
3015 |   "sentence": "['干', '面', '包', '片', '多', '少', '钱']",
3016 |   "labeled entities": "[(0, 3, 'cp')]"
3017 |  },
3018 |  {
3019 |   "sentence": "['婴', '儿', '油', '多', '少', '钱']",
3020 |   "labeled entities": "[(0, 2, 'cp')]"
3021 |  },
3022 |  {
3023 |   "sentence": "['沐', '浴', '条', '多', '少', '钱']",
3024 |   "labeled entities": "[(0, 2, 'cp')]"
3025 |  },
3026 |  {
3027 |   "sentence": "['我', '要', '买', '酒', '水']",
3028 |   "labeled entities": "[(3, 4, 'cp')]"
3029 |  },
3030 |  {
3031 |   "sentence": "['我', '要', '买', '和', '路', '雪']",
3032 |   "labeled entities": "[(3, 5, 'pp')]"
3033 |  },
3034 |  {
3035 |   "sentence": "['我', '要', '买', '饭', '盒', '袋', ' ', '手', '提', '袋']",
3036 |   "labeled entities": "[(3, 5, 'cp'), (7, 9, 'cp')]"
3037 |  },
3038 |  {
3039 |   "sentence": "['我', '要', '买', '槟', '榔']",
3040 |   "labeled entities": "[(3, 4, 'cp')]"
3041 |  },
3042 |  {
3043 |   "sentence": "['我', '要', '买', '龟', '苓', '膏', '梧', '州']",
3044 |   "labeled entities": "[(3, 5, 'cp')]"
3045 |  },
3046 |  {
3047 |   "sentence": "['我', '要', '买', 'b', 'o', 'o', 't', 's']",
3048 |   "labeled entities": "[(3, 7, 'pp')]"
3049 |  },
3050 |  {
3051 |   "sentence": "['乐', '事', '黄', '瓜', '多', '少', '钱']",
3052 |   "labeled entities": "[(0, 1, 'pp')]"
3053 |  },
3054 |  {
3055 |   "sentence": "['我', '要', '买', '葡', '萄', '干', '独', '立', '小', '包', '装']",
3056 |   "labeled entities": "[(3, 5, 'cp')]"
3057 |  },
3058 |  {
3059 |   "sentence": "['我', '要', '买', '柠', '檬', '水', '整', '箱']",
3060 |   "labeled entities": "[(3, 5, 'cp')]"
3061 |  },
3062 |  {
3063 |   "sentence": "['调', '味', '酱', '多', '少', '钱']",
3064 |   "labeled entities": "[(0, 2, 'cp')]"
3065 |  },
3066 |  {
3067 |   "sentence": "['汉', '服']",
3068 |   "labeled entities": "[(0, 1, 'cp')]"
3069 |  },
3070 |  {
3071 |   "sentence": "['谷', '粒', '多', '黑', '谷', '牛', '奶', '多', '少', '钱']",
3072 |   "labeled entities": "[(0, 2, 'pp'), (3, 4, 'xh'), (5, 6, 'cp')]"
3073 |  },
3074 |  {
3075 |   "sentence": "['束', '腹', '带', '多', '少', '钱']",
3076 |   "labeled entities": "[(0, 2, 'cp')]"
3077 |  },
3078 |  {
3079 |   "sentence": "['瓶', '装', '多', '少', '钱']",
3080 |   "labeled entities": "[]"
3081 |  },
3082 |  {
3083 |   "sentence": "['网', '上', '买', '手', '机', '靠', '谱', '吗']",
3084 |   "labeled entities": "[(3, 4, 'cp')]"
3085 |  },
3086 |  {
3087 |   "sentence": "['我', '要', '买', '亮', '净', '洁', '厕', '精']",
3088 |   "labeled entities": "[(3, 4, 'pp'), (5, 7, 'cp')]"
3089 |  },
3090 |  {
3091 |   "sentence": "['子', '初', '蚊', '香', '液', '多', '少', '钱']",
3092 |   "labeled entities": "[(0, 1, 'pp'), (2, 4, 'cp')]"
3093 |  },
3094 |  {
3095 |   "sentence": "['我', '要', '买', '转', '换', '器', '插', '头']",
3096 |   "labeled entities": "[(3, 7, 'cp')]"
3097 |  },
3098 |  {
3099 |   "sentence": "['我', '要', '买', '洗', '发', '水', '飘', '柔']",
3100 |   "labeled entities": "[(3, 5, 'cp'), (6, 7, 'pp')]"
3101 |  },
3102 |  {
3103 |   "sentence": "['好', '奇', '银', '装', '纸', '尿', '裤', '多', '少', '钱']",
3104 |   "labeled entities": "[(0, 1, 'pp'), (2, 3, 'xh'), (4, 6, 'cp')]"
3105 |  },
3106 |  {
3107 |   "sentence": "['我', '要', '买', '安', '慕', '希', '酸', '奶', '香', '草', '味']",
3108 |   "labeled entities": "[(3, 5, 'pp'), (6, 7, 'cp')]"
3109 |  },
3110 |  {
3111 |   "sentence": "['卫', '生', '纸', '无', '芯', '多', '少', '钱']",
3112 |   "labeled entities": "[(0, 2, 'cp')]"
3113 |  },
3114 |  {
3115 |   "sentence": "['多', '芬', '喷', '雾', '多', '少', '钱']",
3116 |   "labeled entities": "[(0, 1, 'pp'), (2, 3, 'cp')]"
3117 |  },
3118 |  {
3119 |   "sentence": "['零', '手', '付', '买', '手', '机']",
3120 |   "labeled entities": "[(4, 5, 'cp')]"
3121 |  },
3122 |  {
3123 |   "sentence": "['一', '次', '性', '纸', '杯', '多', '少', '钱']",
3124 |   "labeled entities": "[(3, 4, 'cp')]"
3125 |  },
3126 |  {
3127 |   "sentence": "['我', '要', '买', '婴', '儿', '磨', '牙']",
3128 |   "labeled entities": "[]"
3129 |  },
3130 |  {
3131 |   "sentence": "['连', '体', '裤']",
3132 |   "labeled entities": "[(0, 2, 'cp')]"
3133 |  },
3134 |  {
3135 |   "sentence": "['我', '要', '买', '消', '毒', '器']",
3136 |   "labeled entities": "[(3, 5, 'cp')]"
3137 |  },
3138 |  {
3139 |   "sentence": "['天', '多', '少', '钱']",
3140 |   "labeled entities": "[]"
3141 |  },
3142 |  {
3143 |   "sentence": "['外', '套', '男']",
3144 |   "labeled entities": "[(0, 1, 'cp')]"
3145 |  },
3146 |  {
3147 |   "sentence": "['高', '跟', '鞋', '夏', '季', '多', '少', '钱']",
3148 |   "labeled entities": "[(0, 2, 'cp')]"
3149 |  },
3150 |  {
3151 |   "sentence": "['我', '要', '买', '沙', '士']",
3152 |   "labeled entities": "[(3, 4, 'cp')]"
3153 |  },
3154 |  {
3155 |   "sentence": "['我', '要', '买', '一', '叶', '子']",
3156 |   "labeled entities": "[(3, 5, 'pp')]"
3157 |  },
3158 |  {
3159 |   "sentence": "['我', '要', '买', '个', '老', '人', '机']",
3160 |   "labeled entities": "[(4, 6, 'cp')]"
3161 |  },
3162 |  {
3163 |   "sentence": "['我', '要', '买', '汉', '堡', '饼']",
3164 |   "labeled entities": "[(3, 5, 'cp')]"
3165 |  },
3166 |  {
3167 |   "sentence": "['我', '要', '买', '茶', '花', '衣', '架']",
3168 |   "labeled entities": "[(3, 4, 'pp'), (5, 6, 'cp')]"
3169 |  },
3170 |  {
3171 |   "sentence": "['我', '要', '买', '调', '料', '罐', ' ', '玻', '璃']",
3172 |   "labeled entities": "[(3, 5, 'cp'), (7, 8, 'yl')]"
3173 |  },
3174 |  {
3175 |   "sentence": "['我', '要', '买', '果', '园', '老', '农']",
3176 |   "labeled entities": "[(3, 6, 'pp')]"
3177 |  },
3178 |  {
3179 |   "sentence": "['我', '要', '买', '厕', '纸', '卫', '生', '纸']",
3180 |   "labeled entities": "[(3, 4, 'cp'), (5, 7, 'cp')]"
3181 |  },
3182 |  {
3183 |   "sentence": "['我', '要', '买', '日', '本', '牙', '刷']",
3184 |   "labeled entities": "[(5, 6, 'cp')]"
3185 |  },
3186 |  {
3187 |   "sentence": "['我', '要', '买', '拉', '杆', '箱', '女']",
3188 |   "labeled entities": "[(3, 5, 'cp')]"
3189 |  },
3190 |  {
3191 |   "sentence": "['我', '要', '买', '泡', '茶', '壶']",
3192 |   "labeled entities": "[(4, 5, 'cp')]"
3193 |  }
3194 | ]


--------------------------------------------------------------------------------
/main.py:
--------------------------------------------------------------------------------
 1 | import argparse
 2 | import os
 3 | import json
 4 | 
 5 | import torch
 6 | from pytorch_pretrained_bert import BertAdam
 7 | 
 8 | from utils import UnitAlphabet, LabelAlphabet
 9 | from model import PhraseClassifier
10 | from misc import fix_random_seed
11 | from utils import corpus_to_iterator, Procedure
12 | 
13 | 
14 | if __name__ == "__main__":
15 |     parser = argparse.ArgumentParser()
16 | 
17 |     parser.add_argument("--data_dir", "-dd", type=str, required=True)
18 |     parser.add_argument("--check_dir", "-cd", type=str, required=True)
19 |     parser.add_argument("--resource_dir", "-rd", type=str, required=True)
20 |     parser.add_argument("--random_state", "-rs", type=int, default=0)
21 |     parser.add_argument("--epoch_num", "-en", type=int, default=40)
22 |     parser.add_argument("--batch_size", "-bs", type=int, default=16)
23 | 
24 |     parser.add_argument("--negative_rate", "-nr", type=float, default=0.35)
25 |     parser.add_argument("--warmup_proportion", "-wp", type=float, default=0.1)
26 |     parser.add_argument("--hidden_dim", "-hd", type=int, default=256)
27 |     parser.add_argument("--dropout_rate", "-dr", type=float, default=0.4)
28 |     parser.add_argument("--CLloss_percent", "-lp", type=float, default=0.1)
29 |     parser.add_argument("--score_percent", "-sp", type=float, default=0.5)
30 |     parser.add_argument("--cl_scale", "-cs", type=int, default=100)
31 |     parser.add_argument("--cl_temp", "-temp", type=float, default=0.1)
32 |     parser.add_argument("--use_detach", "-ud", type=bool, default=False)
33 | 
34 | 
35 |     args = parser.parse_args()
36 |     print(json.dumps(args.__dict__, indent=True), end="\n\n")
37 | 
38 |     fix_random_seed(args.random_state)
39 |     lexical_vocab = UnitAlphabet(os.path.join(args.resource_dir, "bert-base-chinese", "vocab.txt"))
40 |     label_vocab = LabelAlphabet()
41 | 
42 |     train_loader = corpus_to_iterator(os.path.join(args.data_dir, "train.json"), args.batch_size, True, label_vocab)
43 |     dev_loader = corpus_to_iterator(os.path.join(args.data_dir, "dev.json"), args.batch_size, False)
44 |     test_loader = corpus_to_iterator(os.path.join(args.data_dir, "test.json"), args.batch_size, False)
45 | 
46 |     bert_path = os.path.join(args.resource_dir, "bert-base-chinese", "model.pt")
47 |     model = PhraseClassifier(lexical_vocab, label_vocab, args.hidden_dim,
48 |                              args.dropout_rate, args.negative_rate,
49 |                              args.CLloss_percent, args.score_percent,
50 |                              args.cl_scale, args.cl_temp, args.use_detach,
51 |                              bert_path)
52 | 
53 |     model = model.cuda() if torch.cuda.is_available() else model.cpu()
54 | 
55 | 
56 |     all_parameters = list(model.named_parameters())
57 |     no_decay = ['bias', 'LayerNorm.bias', 'LayerNorm.weight']
58 |     grouped_param = [{'params': [p for n, p in all_parameters if not any(nd in n for nd in no_decay)], 'weight_decay': 0.01},
59 |                      {'params': [p for n, p in all_parameters if any(nd in n for nd in no_decay)], 'weight_decay': 0.00}]
60 |     total_steps = int(len(train_loader) * (args.epoch_num + 1))
61 |     optimizer = BertAdam(grouped_param, lr=1e-5, warmup=args.warmup_proportion, t_total=total_steps)
62 | 
63 |     if not os.path.exists(args.check_dir):
64 |         os.makedirs(args.check_dir)
65 |     best_dev = 0.0
66 |     best_test = 0.0
67 |     script_path = os.path.join(args.resource_dir, "conlleval.pl")
68 |     checkpoint_path = os.path.join(args.check_dir, "model.pt")
69 |     for epoch_i in range(0, args.epoch_num + 1):
70 |         loss, train_time, dict_center = Procedure.train(model, train_loader, optimizer)
71 |         print("[Epoch {:3d}] loss on train set is {:.5f} using {:.3f} secs".format(epoch_i, loss, train_time))
72 | 
73 |         dev_f1, dev_time = Procedure.test(model, dev_loader, script_path, dict_center)
74 |         print("(Epoch {:3d}) f1 score on dev set is {:.5f} using {:.3f} secs".format(epoch_i, dev_f1, dev_time))
75 | 
76 |         test_f1, test_time = Procedure.test(model, test_loader, script_path, dict_center)
77 |         print("{{Epoch {:3d}}} f1 score on test set is {:.5f} using {:.3f} secs".format(epoch_i, test_f1, test_time))
78 | 
79 |         if test_f1 > best_test:
80 |             best_test = test_f1
81 | 
82 |         if dev_f1 > best_dev:
83 |             best_dev = dev_f1
84 | 
85 |             print("\n<Epoch {:3d}> save best dev model with score: {:.5f} in terms of test set".format(epoch_i, test_f1))
86 |             torch.save(model, checkpoint_path)
87 |         print("\nbest test f1 score: {:.5f}".format(best_test))
88 |         print(end="\n\n")
89 | 


--------------------------------------------------------------------------------
/misc.py:
--------------------------------------------------------------------------------
  1 | import time
  2 | import json
  3 | import codecs
  4 | import os
  5 | import numpy as np
  6 | import random
  7 | 
  8 | import torch
  9 | 
 10 | 
 11 | def iterative_support(func, query):
 12 |     if isinstance(query, (list, tuple, set)):
 13 |         return [iterative_support(func, i) for i in query]
 14 |     return func(query)
 15 | 
 16 | 
 17 | def fix_random_seed(state_val):
 18 |     random.seed(state_val)
 19 |     np.random.seed(state_val)
 20 | 
 21 |     if torch.cuda.is_available():
 22 |         torch.cuda.manual_seed(state_val)
 23 |         torch.cuda.manual_seed_all(state_val)
 24 | 
 25 |         torch.backends.cudnn.deterministic = True
 26 |         torch.backends.cudnn.benchmark = False
 27 | 
 28 |     torch.manual_seed(state_val)
 29 |     torch.random.manual_seed(state_val)
 30 | 
 31 | 
 32 | def flat_list(h_list):
 33 |     e_list = []
 34 | 
 35 |     for item in h_list:
 36 |         if isinstance(item, list):
 37 |             e_list.extend(flat_list(item))
 38 |         else:
 39 |             e_list.append(item)
 40 |     return e_list
 41 | 
 42 | 
 43 | def f1_score(sent_list, pred_list, gold_list, script_path):
 44 |     fn_out = 'eval_%04d.txt' % random.randint(0, 10000)
 45 |     if os.path.isfile(fn_out):
 46 |         os.remove(fn_out)
 47 | 
 48 |     text_file = open(fn_out, mode='w', encoding='utf-8')
 49 |     for i, words in enumerate(sent_list):
 50 |         tags_1 = gold_list[i]
 51 |         tags_2 = pred_list[i]
 52 |         for j, word in enumerate(words):
 53 |             tag_1 = tags_1[j]
 54 |             tag_2 = tags_2[j]
 55 |             text_file.write('%s\t%s\t%s\n' % (word, tag_1, tag_2))
 56 |         text_file.write('\n')
 57 |     text_file.close()
 58 | 
 59 |     cmd = 'perl %s -d "\t" < %s' % (script_path, fn_out)
 60 |     msg = '\nStandard CoNNL perl script (author: Erik Tjong Kim Sang <erikt@uia.ua.ac.be>, version: 2004-01-26):\n'
 61 |     msg += ''.join(os.popen(cmd).readlines())
 62 |     time.sleep(1.0)
 63 |     if fn_out.startswith('eval_') and os.path.exists(fn_out):
 64 |         os.remove(fn_out)
 65 |     #print(msg)
 66 |     return float(msg.split('\n')[3].split(':')[-1].strip())
 67 | 
 68 | 
 69 | def iob_tagging(entities, s_len):
 70 |     tags = ["O"] * s_len
 71 | 
 72 |     for el, er, et in entities:
 73 |         for i in range(el, er + 1):
 74 |             if i == el:
 75 |                 tags[i] = "B-" + et
 76 |             else:
 77 |                 tags[i] = "I-" + et
 78 |     return tags
 79 | 
 80 | 
 81 | def conflict_judge(line_x, line_y):
 82 |     if line_x[0] == line_y[0]:
 83 |         return True
 84 |     if line_x[0] < line_y[0]:
 85 |         if line_x[1] >= line_y[0]:
 86 |             return True
 87 |     if line_x[0] > line_y[0]:
 88 |         if line_x[0] <= line_y[1]:
 89 |             return True
 90 |     return False
 91 | 
 92 | 
 93 | def extract_json_data(file_path):
 94 |     with codecs.open(file_path, "r", "utf-8") as fr:
 95 |         dataset = json.load(fr)
 96 |     return dataset
 97 | 
 98 | 
 99 | def sim_matrix(a, b, eps=1e-8):
100 |     a_n, b_n = a.norm(dim=1)[:, None], b.norm(dim=1)[:, None]
101 |     a_norm = a / torch.max(a_n, eps * torch.ones_like(a_n))
102 |     b_norm = b / torch.max(b_n, eps * torch.ones_like(b_n))
103 |     sim_mt = torch.mm(a_norm, b_norm.transpose(0, 1))
104 |     return sim_mt
105 | 
106 | 
107 | def contrastive_loss(embedding, label, detach = False, temp=0.1, scale=100):
108 |     if detach:
109 |         cosine_sim = sim_matrix(embedding,embedding).detach() 
110 |         dis = cosine_sim[~torch.eye(cosine_sim.shape[0], dtype=torch.bool)].reshape(cosine_sim.shape[0], -1).detach()
111 |     else:
112 |         cosine_sim = sim_matrix(embedding, embedding)
113 |         dis = cosine_sim[~torch.eye(cosine_sim.shape[0], dtype=torch.bool)].reshape(cosine_sim.shape[0], -1)
114 |     
115 |     
116 |     dis = dis / temp
117 |     cosine_sim = cosine_sim / temp
118 |     
119 |     dis = torch.exp(dis)
120 |     cosine_sim = torch.exp(cosine_sim)
121 | 
122 |     
123 |     row_sum = []
124 |     for i in range(len(embedding)):
125 |         row_sum.append(sum(dis[i]))
126 |     
127 |     contrastive_loss = 0
128 |     for i in range(len(embedding)):
129 |         n_i = label.tolist().count(label[i]) - 1
130 |         inner_sum = 0
131 |         for j in range(len(embedding)):
132 |             if label[i] == label[j] and i != j:
133 |                 inner_sum = inner_sum + torch.log(cosine_sim[i][j] / row_sum[i])
134 |         if n_i != 0:
135 |             contrastive_loss += (inner_sum / (-n_i))
136 |         else:
137 |             contrastive_loss += 0
138 |     return contrastive_loss / scale
139 | 
140 | 


--------------------------------------------------------------------------------
/model.py:
--------------------------------------------------------------------------------
  1 | import numpy as np
  2 | 
  3 | import torch
  4 | from torch import nn
  5 | from pytorch_pretrained_bert import BertModel
  6 | 
  7 | from misc import flat_list
  8 | from misc import sim_matrix, contrastive_loss
  9 | from misc import iterative_support, conflict_judge
 10 | from utils import UnitAlphabet, LabelAlphabet
 11 | from sklearn.metrics.pairwise import cosine_similarity
 12 | 
 13 | 
 14 | class PhraseClassifier(nn.Module):
 15 | 
 16 |     def __init__(self,
 17 |                  lexical_vocab: UnitAlphabet,
 18 |                  label_vocab: LabelAlphabet,
 19 |                  hidden_dim: int,
 20 |                  dropout_rate: float,
 21 |                  neg_rate: float,
 22 |                  clloss_percent: float,
 23 |                  score_percent: float,
 24 |                  cl_scale: int,
 25 |                  cl_temp: float,
 26 |                  use_detach: bool,
 27 |                  bert_path: str):
 28 |         super(PhraseClassifier, self).__init__()
 29 | 
 30 |         self._lexical_vocab = lexical_vocab
 31 |         self._label_vocab = label_vocab
 32 |         self._neg_rate = neg_rate
 33 |         self._clloss_percent = clloss_percent
 34 |         self._score_percent = score_percent
 35 |         self._cl_scale = cl_scale
 36 |         self._cl_temp = cl_temp
 37 |         self._use_detach = use_detach
 38 |         self._encoder = BERT(bert_path)
 39 |         self._classifier = MLP(self._encoder.dimension * 4, hidden_dim, len(label_vocab), dropout_rate)
 40 |         self._criterion = nn.NLLLoss()
 41 | 
 42 |     def forward(self, var_h, **kwargs):
 43 |         con_repr = self._encoder(var_h, kwargs["mask_mat"], kwargs["starts"])
 44 | 
 45 |         batch_size, token_num, hidden_dim = con_repr.size()
 46 |         ext_row = con_repr.unsqueeze(2).expand(batch_size, token_num, token_num, hidden_dim)
 47 |         ext_column = con_repr.unsqueeze(1).expand_as(ext_row)
 48 |         table = torch.cat([ext_row, ext_column, ext_row - ext_column, ext_row * ext_column], dim=-1)
 49 |         return self._classifier(table), self._classifier.get_dense(table)
 50 | 
 51 |     def _pre_process_input(self, utterances):
 52 |         lengths = [len(s) for s in utterances]
 53 |         max_len = max(lengths)
 54 |         pieces = iterative_support(self._lexical_vocab.tokenize, utterances)
 55 |         units, positions = [], []
 56 | 
 57 |         for tokens in pieces:
 58 |             units.append(flat_list(tokens))
 59 |             cum_list = np.cumsum([len(p) for p in tokens]).tolist()
 60 |             positions.append([0] + cum_list[:-1])
 61 | 
 62 |         sizes = [len(u) for u in units]
 63 |         max_size = max(sizes)
 64 |         cls_sign = self._lexical_vocab.CLS_SIGN
 65 |         sep_sign = self._lexical_vocab.SEP_SIGN
 66 |         pad_sign = self._lexical_vocab.PAD_SIGN
 67 |         pad_unit = [[cls_sign] + s + [sep_sign] + [pad_sign] * (max_size - len(s)) for s in units]
 68 |         starts = [[ln + 1 for ln in u] + [max_size + 1] * (max_len - len(u)) for u in positions]
 69 | 
 70 |         var_unit = torch.LongTensor([self._lexical_vocab.index(u) for u in pad_unit])
 71 |         attn_mask = torch.LongTensor([[1] * (lg + 2) + [0] * (max_size - lg) for lg in sizes])
 72 |         var_start = torch.LongTensor(starts)
 73 | 
 74 |         if torch.cuda.is_available():
 75 |             var_unit = var_unit.cuda()
 76 |             attn_mask = attn_mask.cuda()
 77 |             var_start = var_start.cuda()
 78 |         return var_unit, attn_mask, var_start, lengths
 79 | 
 80 |     def _pre_process_output(self, entities, lengths):
 81 |         positions, labels = [], []
 82 |         batch_size = len(entities)
 83 | 
 84 |         for utt_i in range(0, batch_size):
 85 |             for segment in entities[utt_i]:
 86 |                 positions.append((utt_i, segment[0], segment[1]))
 87 |                 labels.append(segment[2])
 88 | 
 89 |         for utt_i in range(0, batch_size):
 90 |             reject_set = [(e[0], e[1]) for e in entities[utt_i]]
 91 |             s_len = lengths[utt_i]
 92 |             neg_num = int(s_len * self._neg_rate) + 1
 93 | 
 94 |             candies = flat_list([[(i, j) for j in range(i, s_len) if (i, j) not in reject_set] for i in range(s_len)])
 95 |             if len(candies) > 0:
 96 |                 sample_num = min(neg_num, len(candies))
 97 |                 assert sample_num > 0
 98 | 
 99 |                 np.random.shuffle(candies)
100 |                 for i, j in candies[:sample_num]:
101 |                     positions.append((utt_i, i, j))
102 |                     labels.append("O")
103 | 
104 |         var_lbl = torch.LongTensor(iterative_support(self._label_vocab.index, labels))
105 |         if torch.cuda.is_available():
106 |             var_lbl = var_lbl.cuda()
107 |         return positions, var_lbl
108 | 
109 | 
110 |     def estimate_CL(self, sentences, segments):
111 |         var_sent, attn_mask, start_mat, lengths = self._pre_process_input(sentences)
112 |         score_t, embedding_t = self(var_sent, mask_mat=attn_mask, starts=start_mat)
113 | 
114 |         positions, targets = self._pre_process_output(segments, lengths)
115 |         targets = targets.cuda()
116 |         flat_s = torch.cat([score_t[[i], j, k] for i, j, k in positions], dim=0).cuda()
117 |         flat_e = torch.cat([embedding_t[[i], j, k] for i, j, k in positions], dim=0).cuda()
118 |         softmax_score = torch.log_softmax(flat_s, dim=-1)
119 |         CE_loss = self._criterion(softmax_score, targets.cuda())
120 |         CL_loss = contrastive_loss(flat_e.cuda(), targets.cuda(), detach = self._use_detach,temp = self._cl_temp, scale = self._cl_scale)
121 | 
122 | 
123 |         dict_center = {}
124 |         dict_num = {}
125 |         target_num = softmax_score.size()[1]
126 |         
127 |         for i in range(0,target_num):
128 |             dict_center[i] = torch.zeros(embedding_t.size()[3])
129 |             dict_num[i] = 0
130 |         for i in range(0,len(targets)):
131 |             dict_num[targets[i].item()] = dict_num[targets[i].item()] + 1
132 |         for i in range(0,len(flat_e)):
133 |             dict_center[targets[i].item()] = dict_center[targets[i].item()] + (flat_e[i].detach().cpu()/dict_num[targets[i].item()])
134 | 
135 |         return self._clloss_percent * CL_loss + (1-self._clloss_percent) * CE_loss, dict_center
136 | 
137 |     def inference(self, sentences, dict_center):
138 |         var_sent, attn_mask, starts, lengths = self._pre_process_input(sentences)
139 |         log_items, embedding_t = self(var_sent, mask_mat=attn_mask, starts=starts)
140 |         score_t = torch.log_softmax(log_items, dim=-1) 
141 | 
142 | 
143 |         bz, len_1 ,len_2 ,hidden_len = embedding_t.size()
144 |         embedding_t = embedding_t.view(-1,hidden_len)
145 |         center_tensor = torch.stack(list(dict_center.values()))
146 |         
147 |         
148 |         distance_score = sim_matrix(embedding_t.cpu(), center_tensor.cpu())
149 |         distance_score = torch.softmax(distance_score, dim=-1)
150 |         distance_score[:,0] = 0 
151 |         distance_score = distance_score.view(bz,len_1,len_2,-1)
152 | 
153 |         
154 |         score_result = (1-self._score_percent) * score_t.cpu() + self._score_percent * distance_score.cpu()
155 |         val_table, idx_table = torch.max(score_result, dim=-1)
156 | 
157 |         listing_it = idx_table.cpu().numpy().tolist()
158 |         listing_vt = val_table.cpu().numpy().tolist()
159 |         label_table = iterative_support(self._label_vocab.get, listing_it)
160 | 
161 |         candidates = []
162 |         for l_mat, v_mat, sent_l in zip(label_table, listing_vt, lengths):
163 |             candidates.append([])
164 |             for i in range(0, sent_l):
165 |                 for j in range(i, sent_l):
166 |                     if l_mat[i][j] != "O":
167 |                         candidates[-1].append((i, j, l_mat[i][j], v_mat[i][j]))
168 | 
169 |         entities = []
170 |         for segments in candidates:
171 |             ordered_seg = sorted(segments, key=lambda e: -e[-1])
172 |             filter_list = []
173 |             for elem in ordered_seg:
174 |                 flag = False
175 |                 current = (elem[0], elem[1])
176 |                 for prior in filter_list:
177 |                     flag = conflict_judge(current, (prior[0], prior[1]))
178 |                     if flag:
179 |                         break
180 |                 if not flag:
181 |                     filter_list.append((elem[0], elem[1], elem[2]))
182 |             entities.append(sorted(filter_list, key=lambda e: e[0]))
183 |         return entities
184 | 
185 | 
186 | class BERT(nn.Module):
187 | 
188 |     def __init__(self, source_path):
189 |         super(BERT, self).__init__()
190 |         self._repr_model = BertModel.from_pretrained(source_path)
191 | 
192 |     @property
193 |     def dimension(self):
194 |         return 768
195 | 
196 |     def forward(self, var_h, attn_mask, starts):
197 |         all_hidden, _ = self._repr_model(var_h, attention_mask=attn_mask, output_all_encoded_layers=False)
198 | 
199 |         batch_size, _, hidden_dim = all_hidden.size()
200 |         _, unit_num = starts.size()
201 |         positions = starts.unsqueeze(-1).expand(batch_size, unit_num, hidden_dim)
202 |         return torch.gather(all_hidden, dim=-2, index=positions)
203 | 
204 | 
205 | class MLP(nn.Module):
206 | 
207 |     def __init__(self, input_dim, hidden_dim, output_dim, dropout_rate):
208 |         super(MLP, self).__init__()
209 | 
210 |         self._densenet = nn.Sequential(nn.Linear(input_dim,hidden_dim),
211 |                                       nn.Tanh())
212 |         self._scorer = nn.Linear(hidden_dim, output_dim)
213 |         self._dropout = nn.Dropout(dropout_rate)
214 | 
215 | 
216 |     def forward(self, var_h):
217 |         return self._scorer(self._densenet(self._dropout(var_h)))
218 | 
219 |     def get_dense(self, var_h):
220 |         return self._densenet(self._dropout(var_h))
221 | 
222 |     def get_score(self, dense):
223 |         return self._scorer(dense)
224 | 


--------------------------------------------------------------------------------
/requirements.txt:
--------------------------------------------------------------------------------
1 | datasets==1.18.4
2 | huggingface-hub==0.4.0
3 | pytorch-pretrained-bert==0.6.2
4 | scikit-learn==1.0.2
5 | scipy==1.5.4
6 | torch==1.10.0+cu111
7 | tqdm==4.31.1
8 | 


--------------------------------------------------------------------------------
/resource/conlleval.pl:
--------------------------------------------------------------------------------
  1 | #!/usr/bin/perl -w
  2 | # conlleval: evaluate result of processing CoNLL-2000 shared task
  3 | # usage:     conlleval [-l] [-r] [-d delimiterTag] [-o oTag] < file
  4 | #            README: http://www.clips.uantwerpen.be/conll2000/chunking/output.html
  5 | # options:   l: generate LaTeX output for tables like in
  6 | #               http://cnts.uia.ac.be/conll2003/ner/example.tex
  7 | #            r: accept raw result tags (without B- and I- prefix;
  8 | #                                       assumes one word per chunk)
  9 | #            d: alternative delimiter tag (default is single space)
 10 | #            o: alternative outside tag (default is O)
 11 | # note:      the file should contain lines with items separated
 12 | #            by $delimiter characters (default space). The final
 13 | #            two items should contain the correct tag and the 
 14 | #            guessed tag in that order. Sentences should be
 15 | #            separated from each other by empty lines or lines
 16 | #            with $boundary fields (default -X-).
 17 | # url:       http://www.clips.uantwerpen.be/conll2000/chunking/
 18 | # started:   1998-09-25
 19 | # version:   2004-01-26
 20 | # author:    Erik Tjong Kim Sang <erikt@uia.ua.ac.be>
 21 | 
 22 | use strict;
 23 | 
 24 | my $false = 0;
 25 | my $true = 42;
 26 | 
 27 | my $boundary = "-X-";     # sentence boundary
 28 | my $correct;              # current corpus chunk tag (I,O,B)
 29 | my $correctChunk = 0;     # number of correctly identified chunks
 30 | my $correctTags = 0;      # number of correct chunk tags
 31 | my $correctType;          # type of current corpus chunk tag (NP,VP,etc.)
 32 | my $delimiter = " ";      # field delimiter
 33 | my $FB1 = 0.0;            # FB1 score (Van Rijsbergen 1979)
 34 | my $firstItem;            # first feature (for sentence boundary checks)
 35 | my $foundCorrect = 0;     # number of chunks in corpus
 36 | my $foundGuessed = 0;     # number of identified chunks
 37 | my $guessed;              # current guessed chunk tag
 38 | my $guessedType;          # type of current guessed chunk tag
 39 | my $i;                    # miscellaneous counter
 40 | my $inCorrect = $false;   # currently processed chunk is correct until now
 41 | my $lastCorrect = "O";    # previous chunk tag in corpus
 42 | my $latex = 0;            # generate LaTeX formatted output
 43 | my $lastCorrectType = ""; # type of previously identified chunk tag
 44 | my $lastGuessed = "O";    # previously identified chunk tag
 45 | my $lastGuessedType = ""; # type of previous chunk tag in corpus
 46 | my $lastType;             # temporary storage for detecting duplicates
 47 | my $line;                 # line
 48 | my $nbrOfFeatures = -1;   # number of features per line
 49 | my $precision = 0.0;      # precision score
 50 | my $oTag = "O";           # outside tag, default O
 51 | my $raw = 0;              # raw input: add B to every token
 52 | my $recall = 0.0;         # recall score
 53 | my $tokenCounter = 0;     # token counter (ignores sentence breaks)
 54 | 
 55 | my %correctChunk = ();    # number of correctly identified chunks per type
 56 | my %foundCorrect = ();    # number of chunks in corpus per type
 57 | my %foundGuessed = ();    # number of identified chunks per type
 58 | 
 59 | my @features;             # features on line
 60 | my @sortedTypes;          # sorted list of chunk type names
 61 | 
 62 | # sanity check
 63 | while (@ARGV and $ARGV[0] =~ /^-/) {
 64 |    if ($ARGV[0] eq "-l") { $latex = 1; shift(@ARGV); }
 65 |    elsif ($ARGV[0] eq "-r") { $raw = 1; shift(@ARGV); }
 66 |    elsif ($ARGV[0] eq "-d") { 
 67 |       shift(@ARGV); 
 68 |       if (not defined $ARGV[0]) { 
 69 |          die "conlleval: -d requires delimiter character"; 
 70 |       }
 71 |       $delimiter = shift(@ARGV);
 72 |    } elsif ($ARGV[0] eq "-o") {
 73 |       shift(@ARGV);
 74 |       if (not defined $ARGV[0]) {
 75 |          die "conlleval: -o requires delimiter character";
 76 |       }
 77 |       $oTag = shift(@ARGV);
 78 |    } else { die "conlleval: unknown argument $ARGV[0]\n"; }
 79 | }
 80 | if (@ARGV) { die "conlleval: unexpected command line argument\n"; }
 81 | # process input
 82 | while (<STDIN>) {
 83 |    chomp($line = $_);
 84 |    @features = split(/$delimiter/,$line);
 85 |    if ($nbrOfFeatures < 0) { $nbrOfFeatures = $#features; }
 86 |    elsif ($nbrOfFeatures != $#features and @features != 0) {
 87 |       printf STDERR "unexpected number of features: %d (%d)\n",
 88 |          $#features+1,$nbrOfFeatures+1;
 89 |       exit(1);
 90 |    }
 91 |    if (@features == 0 or 
 92 |        $features[0] eq $boundary) { @features = ($boundary,"O","O"); }
 93 |    if (@features < 2) { 
 94 |       die "conlleval: unexpected number of features in line $line\n"; 
 95 |    }
 96 |    if ($raw) {
 97 |       if ($features[$#features] eq $oTag) { $features[$#features] = "O"; } 
 98 |       if ($features[$#features-1] eq $oTag) { $features[$#features-1] = "O"; } 
 99 |       if ($features[$#features] ne "O") { 
100 |          $features[$#features] = "B-$features[$#features]";
101 |       }
102 |       if ($features[$#features-1] ne "O") { 
103 |          $features[$#features-1] = "B-$features[$#features-1]";
104 |       }
105 |    }
106 |    # 20040126 ET code which allows hyphens in the types
107 |    if ($features[$#features] =~ /^([^-]*)-(.*)$/) {
108 |       $guessed = $1;
109 |       $guessedType = $2;
110 |    } else { 
111 |       $guessed = $features[$#features]; 
112 |       $guessedType = ""; 
113 |    }
114 |    pop(@features);
115 |    if ($features[$#features] =~ /^([^-]*)-(.*)$/) {
116 |       $correct = $1;
117 |       $correctType = $2;
118 |    } else { 
119 |       $correct = $features[$#features]; 
120 |       $correctType = ""; 
121 |    }
122 |    pop(@features);
123 | #  ($guessed,$guessedType) = split(/-/,pop(@features));
124 | #  ($correct,$correctType) = split(/-/,pop(@features));
125 |    $guessedType = $guessedType ? $guessedType : "";
126 |    $correctType = $correctType ? $correctType : "";
127 |    $firstItem = shift(@features);
128 | 
129 |    # 1999-06-26 sentence breaks should always be counted as out of chunk
130 |    if ( $firstItem eq $boundary ) { $guessed = "O"; }
131 | 
132 |    if ($inCorrect) {
133 |       if ( &endOfChunk($lastCorrect,$correct,$lastCorrectType,$correctType) and
134 |            &endOfChunk($lastGuessed,$guessed,$lastGuessedType,$guessedType) and
135 |            $lastGuessedType eq $lastCorrectType) {
136 |          $inCorrect=$false;
137 |          $correctChunk++;
138 |          $correctChunk{$lastCorrectType} = $correctChunk{$lastCorrectType} ?
139 |              $correctChunk{$lastCorrectType}+1 : 1;
140 |       } elsif ( 
141 |            &endOfChunk($lastCorrect,$correct,$lastCorrectType,$correctType) != 
142 |            &endOfChunk($lastGuessed,$guessed,$lastGuessedType,$guessedType) or
143 |            $guessedType ne $correctType ) {
144 |          $inCorrect=$false; 
145 |       }
146 |    }
147 | 
148 |    if ( &startOfChunk($lastCorrect,$correct,$lastCorrectType,$correctType) and 
149 |         &startOfChunk($lastGuessed,$guessed,$lastGuessedType,$guessedType) and
150 |         $guessedType eq $correctType) { $inCorrect = $true; }
151 | 
152 |    if ( &startOfChunk($lastCorrect,$correct,$lastCorrectType,$correctType) ) {
153 |       $foundCorrect++; 
154 |       $foundCorrect{$correctType} = $foundCorrect{$correctType} ?
155 |           $foundCorrect{$correctType}+1 : 1;
156 |    }
157 |    if ( &startOfChunk($lastGuessed,$guessed,$lastGuessedType,$guessedType) ) {
158 |       $foundGuessed++; 
159 |       $foundGuessed{$guessedType} = $foundGuessed{$guessedType} ?
160 |           $foundGuessed{$guessedType}+1 : 1;
161 |    }
162 |    if ( $firstItem ne $boundary ) { 
163 |       if ( $correct eq $guessed and $guessedType eq $correctType ) { 
164 |          $correctTags++; 
165 |       }
166 |       $tokenCounter++; 
167 |    }
168 | 
169 |    $lastGuessed = $guessed;
170 |    $lastCorrect = $correct;
171 |    $lastGuessedType = $guessedType;
172 |    $lastCorrectType = $correctType;
173 | }
174 | if ($inCorrect) { 
175 |    $correctChunk++;
176 |    $correctChunk{$lastCorrectType} = $correctChunk{$lastCorrectType} ?
177 |        $correctChunk{$lastCorrectType}+1 : 1;
178 | }
179 | 
180 | if (not $latex) {
181 |    # compute overall precision, recall and FB1 (default values are 0.0)
182 |    $precision = 100*$correctChunk/$foundGuessed if ($foundGuessed > 0);
183 |    $recall = 100*$correctChunk/$foundCorrect if ($foundCorrect > 0);
184 |    $FB1 = 2*$precision*$recall/($precision+$recall)
185 |       if ($precision+$recall > 0);
186 |    
187 |    # print overall performance
188 |    printf "processed $tokenCounter tokens with $foundCorrect phrases; ";
189 |    printf "found: $foundGuessed phrases; correct: $correctChunk.\n";
190 |    if ($tokenCounter>0) {
191 |       printf "accuracy: %6.2f%%; ",100*$correctTags/$tokenCounter;
192 |       printf "precision: %6.2f%%; ",$precision;
193 |       printf "recall: %6.2f%%; ",$recall;
194 |       printf "FB1: %6.2f\n",$FB1;
195 |    }
196 | }
197 | 
198 | # sort chunk type names
199 | undef($lastType);
200 | @sortedTypes = ();
201 | foreach $i (sort (keys %foundCorrect,keys %foundGuessed)) {
202 |    if (not($lastType) or $lastType ne $i) { 
203 |       push(@sortedTypes,($i));
204 |    }
205 |    $lastType = $i;
206 | }
207 | # print performance per chunk type
208 | if (not $latex) {
209 |    for $i (@sortedTypes) {
210 |       $correctChunk{$i} = $correctChunk{$i} ? $correctChunk{$i} : 0;
211 |       if (not($foundGuessed{$i})) { $foundGuessed{$i} = 0; $precision = 0.0; }
212 |       else { $precision = 100*$correctChunk{$i}/$foundGuessed{$i}; }
213 |       if (not($foundCorrect{$i})) { $recall = 0.0; }
214 |       else { $recall = 100*$correctChunk{$i}/$foundCorrect{$i}; }
215 |       if ($precision+$recall == 0.0) { $FB1 = 0.0; }
216 |       else { $FB1 = 2*$precision*$recall/($precision+$recall); }
217 |       printf "%17s: ",$i;
218 |       printf "precision: %6.2f%%; ",$precision;
219 |       printf "recall: %6.2f%%; ",$recall;
220 |       printf "FB1: %6.2f  %d\n",$FB1,$foundGuessed{$i};
221 |    }
222 | } else {
223 |    print "        & Precision &  Recall  & F\$_{\\beta=1} \\\\\\hline";
224 |    for $i (@sortedTypes) {
225 |       $correctChunk{$i} = $correctChunk{$i} ? $correctChunk{$i} : 0;
226 |       if (not($foundGuessed{$i})) { $precision = 0.0; }
227 |       else { $precision = 100*$correctChunk{$i}/$foundGuessed{$i}; }
228 |       if (not($foundCorrect{$i})) { $recall = 0.0; }
229 |       else { $recall = 100*$correctChunk{$i}/$foundCorrect{$i}; }
230 |       if ($precision+$recall == 0.0) { $FB1 = 0.0; }
231 |       else { $FB1 = 2*$precision*$recall/($precision+$recall); }
232 |       printf "\n%-7s &  %6.2f\\%% & %6.2f\\%% & %6.2f \\\\",
233 |              $i,$precision,$recall,$FB1;
234 |    }
235 |    print "\\hline\n";
236 |    $precision = 0.0;
237 |    $recall = 0;
238 |    $FB1 = 0.0;
239 |    $precision = 100*$correctChunk/$foundGuessed if ($foundGuessed > 0);
240 |    $recall = 100*$correctChunk/$foundCorrect if ($foundCorrect > 0);
241 |    $FB1 = 2*$precision*$recall/($precision+$recall)
242 |       if ($precision+$recall > 0);
243 |    printf "Overall &  %6.2f\\%% & %6.2f\\%% & %6.2f \\\\\\hline\n",
244 |           $precision,$recall,$FB1;
245 | }
246 | 
247 | exit 0;
248 | 
249 | # endOfChunk: checks if a chunk ended between the previous and current word
250 | # arguments:  previous and current chunk tags, previous and current types
251 | # note:       this code is capable of handling other chunk representations
252 | #             than the default CoNLL-2000 ones, see EACL'99 paper of Tjong
253 | #             Kim Sang and Veenstra http://xxx.lanl.gov/abs/cs.CL/9907006
254 | 
255 | sub endOfChunk {
256 |    my $prevTag = shift(@_);
257 |    my $tag = shift(@_);
258 |    my $prevType = shift(@_);
259 |    my $type = shift(@_);
260 |    my $chunkEnd = $false;
261 | 
262 |    if ( $prevTag eq "B" and $tag eq "B" ) { $chunkEnd = $true; }
263 |    if ( $prevTag eq "B" and $tag eq "O" ) { $chunkEnd = $true; }
264 |    if ( $prevTag eq "I" and $tag eq "B" ) { $chunkEnd = $true; }
265 |    if ( $prevTag eq "I" and $tag eq "O" ) { $chunkEnd = $true; }
266 | 
267 |    if ( $prevTag eq "E" and $tag eq "E" ) { $chunkEnd = $true; }
268 |    if ( $prevTag eq "E" and $tag eq "I" ) { $chunkEnd = $true; }
269 |    if ( $prevTag eq "E" and $tag eq "O" ) { $chunkEnd = $true; }
270 |    if ( $prevTag eq "I" and $tag eq "O" ) { $chunkEnd = $true; }
271 | 
272 |    if ($prevTag ne "O" and $prevTag ne "." and $prevType ne $type) { 
273 |       $chunkEnd = $true; 
274 |    }
275 | 
276 |    # corrected 1998-12-22: these chunks are assumed to have length 1
277 |    if ( $prevTag eq "]" ) { $chunkEnd = $true; }
278 |    if ( $prevTag eq "[" ) { $chunkEnd = $true; }
279 | 
280 |    return($chunkEnd);   
281 | }
282 | 
283 | # startOfChunk: checks if a chunk started between the previous and current word
284 | # arguments:    previous and current chunk tags, previous and current types
285 | # note:         this code is capable of handling other chunk representations
286 | #               than the default CoNLL-2000 ones, see EACL'99 paper of Tjong
287 | #               Kim Sang and Veenstra http://xxx.lanl.gov/abs/cs.CL/9907006
288 | 
289 | sub startOfChunk {
290 |    my $prevTag = shift(@_);
291 |    my $tag = shift(@_);
292 |    my $prevType = shift(@_);
293 |    my $type = shift(@_);
294 |    my $chunkStart = $false;
295 | 
296 |    if ( $prevTag eq "B" and $tag eq "B" ) { $chunkStart = $true; }
297 |    if ( $prevTag eq "I" and $tag eq "B" ) { $chunkStart = $true; }
298 |    if ( $prevTag eq "O" and $tag eq "B" ) { $chunkStart = $true; }
299 |    if ( $prevTag eq "O" and $tag eq "I" ) { $chunkStart = $true; }
300 | 
301 |    if ( $prevTag eq "E" and $tag eq "E" ) { $chunkStart = $true; }
302 |    if ( $prevTag eq "E" and $tag eq "I" ) { $chunkStart = $true; }
303 |    if ( $prevTag eq "O" and $tag eq "E" ) { $chunkStart = $true; }
304 |    if ( $prevTag eq "O" and $tag eq "I" ) { $chunkStart = $true; }
305 | 
306 |    if ($tag ne "O" and $tag ne "." and $prevType ne $type) { 
307 |       $chunkStart = $true; 
308 |    }
309 | 
310 |    # corrected 1998-12-22: these chunks are assumed to have length 1
311 |    if ( $tag eq "[" ) { $chunkStart = $true; }
312 |    if ( $tag eq "]" ) { $chunkStart = $true; }
313 | 
314 |    return($chunkStart);   
315 | }
316 | 


--------------------------------------------------------------------------------
/save/readme.md:
--------------------------------------------------------------------------------
1 | you will get trained models here.
2 | 


--------------------------------------------------------------------------------
/train_EC.sh:
--------------------------------------------------------------------------------
1 | CUDA_VISIBLE_DEVICES=0 python main.py -dd dataset/EC -cd save -rd resource


--------------------------------------------------------------------------------
/train_NEWS.sh:
--------------------------------------------------------------------------------
1 | CUDA_VISIBLE_DEVICES=0 python main.py -dd dataset/MSRA -cd save -rd resource -cs 1000 -ud True


--------------------------------------------------------------------------------
/utils.py:
--------------------------------------------------------------------------------
  1 | import numpy as np
  2 | from tqdm import tqdm
  3 | import time
  4 | 
  5 | import os
  6 | import torch
  7 | from torch.utils.data import DataLoader
  8 | from torch.utils.data import Dataset
  9 | from pytorch_pretrained_bert import BertTokenizer
 10 | 
 11 | from misc import extract_json_data
 12 | from misc import iob_tagging, f1_score
 13 | 
 14 | 
 15 | class UnitAlphabet(object):
 16 | 
 17 |     CLS_SIGN, SEP_SIGN = "[CLS]", "[SEP]"
 18 |     PAD_SIGN, UNK_SIGN = "[PAD]", "[UNK]"
 19 | 
 20 |     def __init__(self, source_path):
 21 |         self._tokenizer = BertTokenizer.from_pretrained(source_path, do_lower_case=False)
 22 | 
 23 |     def tokenize(self, item):
 24 |         return self._tokenizer.tokenize(item)
 25 | 
 26 |     def index(self, items):
 27 |         return self._tokenizer.convert_tokens_to_ids(items)
 28 | 
 29 | 
 30 | class LabelAlphabet(object):
 31 | 
 32 |     def __init__(self):
 33 |         super(LabelAlphabet, self).__init__()
 34 | 
 35 |         self._idx_to_item = []
 36 |         self._item_to_idx = {}
 37 | 
 38 |     def add(self, item):
 39 |         if item not in self._item_to_idx:
 40 |             self._item_to_idx[item] = len(self._idx_to_item)
 41 |             self._idx_to_item.append(item)
 42 | 
 43 |     def get(self, idx):
 44 |         return self._idx_to_item[idx]
 45 | 
 46 |     def index(self, item):
 47 |         return self._item_to_idx[item]
 48 | 
 49 |     def __str__(self):
 50 |         return str(self._item_to_idx)
 51 | 
 52 |     def __len__(self):
 53 |         return len(self._idx_to_item)
 54 | 
 55 | 
 56 | def corpus_to_iterator(file_path, batch_size, if_shuffle, label_vocab=None):
 57 |     material = extract_json_data(file_path)
 58 |     instances = [(eval(e["sentence"]), eval(e["labeled entities"])) for e in material]
 59 | 
 60 |     if label_vocab is not None:
 61 |         label_vocab.add("O")
 62 |         for _, u in instances:
 63 |             for _, _, l in u:
 64 |                 label_vocab.add(l)
 65 | 
 66 |     class _DataSet(Dataset):
 67 | 
 68 |         def __init__(self, elements):
 69 |             self._elements = elements
 70 | 
 71 |         def __getitem__(self, item):
 72 |             return self._elements[item]
 73 | 
 74 |         def __len__(self):
 75 |             return len(self._elements)
 76 | 
 77 |     def distribute(elements):
 78 |         sentences, entities = [], []
 79 |         for s, e in elements:
 80 |             sentences.append(s)
 81 |             entities.append(e)
 82 |         return sentences, entities
 83 | 
 84 |     wrap_data = _DataSet(instances)
 85 |     return DataLoader(wrap_data, batch_size, if_shuffle, collate_fn=distribute)
 86 | 
 87 | 
 88 | class Procedure(object):
 89 | 
 90 |     @staticmethod
 91 |     def train(model, dataset, optimizer):
 92 |         model.train()
 93 |         time_start, total_penalties = time.time(), 0.0
 94 |         batch_num = len(dataset)
 95 |         dict_result = {}
 96 |         flag_num = 0
 97 |         for batch in tqdm(dataset, ncols=50):
 98 |             loss, dict_center = model.estimate_CL(*batch)
 99 | 
100 |             if flag_num == 0:
101 |                 for i in range(0,len(dict_center.keys())):
102 |                     dict_result[i] = dict_center[i]/ batch_num
103 |             else:
104 |                 for i in range(0,len(dict_center.keys())):
105 |                     dict_result[i] = dict_result[i] + (dict_center[i] / batch_num)
106 | 
107 |             flag_num = flag_num + 1
108 | 
109 |             total_penalties += loss.cpu().item()
110 |             optimizer.zero_grad()
111 |             loss.backward()
112 | 
113 |             torch.nn.utils.clip_grad_norm_(model.parameters(), 1.5)
114 |             
115 |             optimizer.step()
116 | 
117 | 
118 | 
119 |         time_con = time.time() - time_start
120 |         return total_penalties, time_con, dict_result
121 | 
122 |     @staticmethod
123 |     def test(model, dataset, eval_path, dict_center):
124 |         model.eval()
125 |         time_start = time.time()
126 |         seqs, outputs, oracles = [], [], []
127 | 
128 |         for sentences, segments in tqdm(dataset, ncols=50):
129 |             with torch.no_grad():
130 |                 predictions = model.inference(sentences, dict_center)
131 | 
132 |             seqs.extend(sentences)
133 |             outputs.extend([iob_tagging(e, len(u)) for e, u in zip(predictions, sentences)])
134 |             oracles.extend([iob_tagging(e, len(u)) for e, u in zip(segments, sentences)])
135 | 
136 |         out_f1 = f1_score(seqs, outputs, oracles, eval_path)
137 |         return out_f1, time.time() - time_start
138 | 


--------------------------------------------------------------------------------