├── LICENSE ├── README.md ├── __pycache__ └── data_utils.cpython-36.pyc ├── data └── train ├── data_utils.py ├── model.py ├── models ├── checkpoint ├── data_map.pkl ├── transR.ckpt.data-00000-of-00001 ├── transR.ckpt.index └── transR.ckpt.meta └── transR.py /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | ### Cluster-based-TransR 2 | 3 | Reference [Learning Entity and Relation Embeddings for Knowledge Graph Completion](http://nlp.csai.tsinghua.edu.cn/~lzy/publications/aaai2015_transr.pdf) 4 | 5 | 6 | ### TransR Model 7 | 8 | tr = TransR() 9 | tr.predict_relations("磁器口", "重庆") 10 | > the relation between 磁器口 and 重庆 is 景点 11 | -------------------------------------------------------------------------------- /__pycache__/data_utils.cpython-36.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yanwii/Cluster-based-TransR/bc50bc2fb2bc7d55e76e181a942894c5cfd47931/__pycache__/data_utils.cpython-36.pyc -------------------------------------------------------------------------------- /data/train: -------------------------------------------------------------------------------- 1 | 杭州,中国,省会 2 | 重庆,中国,省会 3 | 台湾,中国,省会 4 | 加州,美国,省会 5 | 杭州电子科技大学,杭州,大学 6 | 浙江大学,杭州,大学 7 | 北京大学,北京,大学 8 | 复旦大学,上海,大学 9 | 磁器口,重庆,景点 10 | 西湖,杭州,景点 11 | 故宫,北京,景点 12 | -------------------------------------------------------------------------------- /data_utils.py: -------------------------------------------------------------------------------- 1 | # -*- coding:utf-8 -*- 2 | ''' 3 | @Author: yanwii 4 | @Date: 2018-08-16 15:18:52 5 | ''' 6 | 7 | 8 | class BatchManager(object): 9 | 10 | def __init__(self, batch_size=1): 11 | self.batch_size = batch_size 12 | self.data = [] 13 | self.batch_data = [] 14 | 15 | self.head_vocab = {"unk":0} 16 | self.tail_vocab = {"unk":0} 17 | self.relation_vocab = {"unk":0} 18 | 19 | self.load_data() 20 | self.prepare_batch() 21 | 22 | def add_vocab(self, word, vocab={}): 23 | if word not in vocab: 24 | vocab[word] = len(vocab.keys()) 25 | return vocab[word] 26 | 27 | def load_data(self): 28 | with open("data/train") as fopen: 29 | lines = fopen.readlines() 30 | for line in lines: 31 | head, tail, relation = line.strip().split(",") 32 | 33 | h_v = self.add_vocab(head, self.head_vocab) 34 | t_v = self.add_vocab(tail, self.tail_vocab) 35 | r_v = self.add_vocab(relation, self.relation_vocab) 36 | self.data.append([[h_v], [t_v], [r_v]]) 37 | 38 | self.head_vocab_size = len(self.head_vocab) + 1 39 | self.tail_vocab_size = len(self.tail_vocab) + 1 40 | self.relation_vocab_size = len(self.relation_vocab) + 1 41 | 42 | def prepare_batch(self): 43 | index = 0 44 | while True: 45 | if index + self.batch_size >= len(self.data): 46 | data = self.data[-self.batch_size:] 47 | self.batch_data.append(data) 48 | break 49 | else: 50 | data = self.data[index:index+self.batch_size] 51 | index += self.batch_size 52 | self.batch_data.append(data) 53 | 54 | def iteration(self): 55 | idx = 0 56 | while True: 57 | yield self.batch_data[idx] 58 | idx += 1 59 | if idx > len(self.batch_data)-1: 60 | idx = 0 61 | 62 | def get_batch(self): 63 | for data in self.batch_data: 64 | yield data -------------------------------------------------------------------------------- /model.py: -------------------------------------------------------------------------------- 1 | # -*- coding:utf-8 -*- 2 | ''' 3 | @Author: yanwii 4 | @Date: 2018-08-16 10:43:55 5 | ''' 6 | 7 | import tensorflow as tf 8 | 9 | class ClusterBasedTransR(object): 10 | 11 | def __init__(self): 12 | self.size_of_relation = 256 13 | self.size_of_entity = 128 14 | 15 | def init_model(self): 16 | pass 17 | 18 | def __trans(self): 19 | with tf.variable_scope("trans") as scope: 20 | Mr = tf.get_variable( 21 | name="Mr", 22 | shape=[self.size_of_entity, self.size_of_relation] 23 | ) 24 | 25 | hr = tf.matmul(self.h, Mr) 26 | tr = tf.matmul(self.t, Mr) 27 | 28 | -------------------------------------------------------------------------------- /models/checkpoint: -------------------------------------------------------------------------------- 1 | model_checkpoint_path: "transR.ckpt" 2 | all_model_checkpoint_paths: "transR.ckpt" 3 | -------------------------------------------------------------------------------- /models/data_map.pkl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yanwii/Cluster-based-TransR/bc50bc2fb2bc7d55e76e181a942894c5cfd47931/models/data_map.pkl -------------------------------------------------------------------------------- /models/transR.ckpt.data-00000-of-00001: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yanwii/Cluster-based-TransR/bc50bc2fb2bc7d55e76e181a942894c5cfd47931/models/transR.ckpt.data-00000-of-00001 -------------------------------------------------------------------------------- /models/transR.ckpt.index: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yanwii/Cluster-based-TransR/bc50bc2fb2bc7d55e76e181a942894c5cfd47931/models/transR.ckpt.index -------------------------------------------------------------------------------- /models/transR.ckpt.meta: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yanwii/Cluster-based-TransR/bc50bc2fb2bc7d55e76e181a942894c5cfd47931/models/transR.ckpt.meta -------------------------------------------------------------------------------- /transR.py: -------------------------------------------------------------------------------- 1 | # -*- coding:utf-8 -*- 2 | ''' 3 | @Author: yanwii 4 | @Date: 2018-08-16 10:43:55 5 | ''' 6 | 7 | import pickle 8 | 9 | import numpy as np 10 | import tensorflow as tf 11 | 12 | from data_utils import BatchManager 13 | 14 | class TransR(object): 15 | 16 | def __init__(self): 17 | self.size_of_relation = 100 18 | self.size_of_entity = 100 19 | 20 | self.head_input_size = 10 21 | self.tail_input_size = 10 22 | self.relation_input_size = 10 23 | 24 | self.checkpoint_dir = "./models/" 25 | self.checkpoint_path = "./models/transR.ckpt" 26 | 27 | def init_model(self): 28 | self.__placeholder() 29 | self.__head() 30 | self.__tail() 31 | self.__relation() 32 | self.__trans() 33 | self.__optimizer() 34 | 35 | def __placeholder(self): 36 | self.head_inputs = tf.placeholder( 37 | shape=[None, 1], 38 | dtype=tf.int32, 39 | name="head" 40 | ) 41 | self.tail_inputs = tf.placeholder( 42 | shape=[None, 1], 43 | dtype=tf.int32, 44 | name="tail" 45 | ) 46 | self.relation_inputs = tf.placeholder( 47 | shape=[None, 1], 48 | dtype=tf.int32, 49 | name="relation" 50 | ) 51 | 52 | self.dropout = tf.placeholder( 53 | dtype=tf.float32, 54 | shape=None, 55 | name="dropout" 56 | ) 57 | 58 | def __head(self): 59 | with tf.variable_scope("head_embedding") as scope: 60 | embedding_matrix = tf.get_variable( 61 | name="head_embedding_matrix", 62 | shape=[self.head_input_size, self.size_of_entity], 63 | dtype=tf.float32 64 | ) 65 | head_embedding = tf.nn.embedding_lookup( 66 | embedding_matrix, self.head_inputs 67 | ) 68 | self.head = tf.nn.dropout( 69 | head_embedding, self.dropout 70 | ) 71 | 72 | def __tail(self): 73 | with tf.variable_scope("tail_embedding") as scope: 74 | embedding_matrix = tf.get_variable( 75 | name="tail_embedding_matrix", 76 | shape=[self.tail_input_size, self.size_of_entity], 77 | dtype=tf.float32 78 | ) 79 | tail_embedding = tf.nn.embedding_lookup( 80 | embedding_matrix, self.tail_inputs 81 | ) 82 | self.tail = tf.nn.dropout( 83 | tail_embedding, self.dropout 84 | ) 85 | 86 | def __relation(self): 87 | with tf.variable_scope("relation_embedding") as scope: 88 | embedding_matrix = tf.get_variable( 89 | name="relation_embedding_matrix", 90 | shape=[self.relation_input_size, self.size_of_relation], 91 | dtype=tf.float32 92 | ) 93 | relation_embedding = tf.nn.embedding_lookup( 94 | embedding_matrix, self.relation_inputs 95 | ) 96 | self.relation = tf.nn.dropout( 97 | relation_embedding, self.dropout 98 | ) 99 | 100 | def __trans(self): 101 | with tf.variable_scope("trans") as scope: 102 | self.Mr = tf.get_variable( 103 | name="Mr", 104 | shape=[self.size_of_entity, self.size_of_relation] 105 | ) 106 | self.head = tf.reshape(self.head, shape=[-1, self.size_of_entity]) 107 | self.tail = tf.reshape(self.tail, shape=[-1, self.size_of_entity]) 108 | self.relation = tf.reshape(self.relation, shape=[-1, self.size_of_relation]) 109 | 110 | self.hr = tf.matmul(self.head, self.Mr) 111 | self.tr = tf.matmul(self.tail, self.Mr) 112 | self.r = self.relation 113 | 114 | fr = self.hr + self.r - self.tr 115 | self.logits = tf.reduce_sum(fr * fr, axis=1) 116 | self.loss = tf.reduce_sum(self.logits) 117 | 118 | def __optimizer(self): 119 | params = tf.trainable_variables() 120 | gradients = tf.gradients(self.loss, params) 121 | clipped_gradients, _ = tf.clip_by_global_norm( 122 | gradients, 5) 123 | # Optimization 124 | optimizer = tf.train.GradientDescentOptimizer(0.02) 125 | self.train_op = optimizer.apply_gradients(zip(clipped_gradients, params)) 126 | self.saver = tf.train.Saver(tf.global_variables()) 127 | 128 | def step(self, batch, sess): 129 | heads = [i[0] for i in batch] 130 | tails = [i[1] for i in batch] 131 | relations = [i[2] for i in batch] 132 | 133 | feed = { 134 | self.head_inputs:heads, 135 | self.tail_inputs:tails, 136 | self.relation_inputs:relations, 137 | self.dropout:0.5 138 | } 139 | loss,_ = sess.run([self.loss, self.train_op], feed_dict=feed) 140 | return loss 141 | 142 | def train(self): 143 | batch_manager = BatchManager() 144 | self.head_input_size = batch_manager.head_vocab_size 145 | self.tail_input_size = batch_manager.tail_vocab_size 146 | self.relation_input_size = batch_manager.relation_vocab_size 147 | data_map = { 148 | "head_size":self.head_input_size, 149 | "tail_size":self.tail_input_size, 150 | "relation_size":self.relation_input_size, 151 | "head_vocab":batch_manager.head_vocab, 152 | "tail_vocab":batch_manager.tail_vocab, 153 | "relation_vocab":batch_manager.relation_vocab 154 | } 155 | f = open("models/data_map.pkl", "wb") 156 | pickle.dump(data_map, f) 157 | f.close() 158 | 159 | self.init_model() 160 | with tf.Session() as sess: 161 | ckpt = tf.train.get_checkpoint_state(self.checkpoint_dir) 162 | if ckpt and tf.train.checkpoint_exists(ckpt.model_checkpoint_path): 163 | print("[->] restore model") 164 | self.saver.restore(sess, ckpt.model_checkpoint_path) 165 | else: 166 | print("[->] no model, initializing") 167 | sess.run(tf.global_variables_initializer()) 168 | 169 | for i in range(200): 170 | print("epoch {}".format(i)) 171 | for batch in batch_manager.get_batch(): 172 | loss = self.step(batch, sess) 173 | print("\tloss: {}".format(loss)) 174 | self.saver.save(sess, self.checkpoint_path) 175 | 176 | def predict_relations(self, head, tail): 177 | f = open("models/data_map.pkl", "rb") 178 | data_map = pickle.load(f) 179 | f.close() 180 | 181 | self.head_vocab = data_map.get("head_vocab") 182 | self.tail_vocab = data_map.get("tail_vocab") 183 | self.relation_vocab = data_map.get("relation_vocab") 184 | 185 | self.head_input_size = data_map.get("head_size") 186 | self.tail_input_size = data_map.get("tail_size") 187 | self.relation_input_size = data_map.get("relation_size") 188 | 189 | self.init_model() 190 | 191 | with tf.Session() as sess: 192 | ckpt = tf.train.get_checkpoint_state(self.checkpoint_dir) 193 | if ckpt and tf.train.checkpoint_exists(ckpt.model_checkpoint_path): 194 | print("[->] restore model") 195 | self.saver.restore(sess, ckpt.model_checkpoint_path) 196 | else: 197 | print("[->] no model, initializing") 198 | sess.run(tf.global_variables_initializer()) 199 | 200 | relations = list(self.relation_vocab.keys()) 201 | relations_vec = [[self.relation_vocab.get(i)] for i in relations] 202 | 203 | heads_vec = [[self.head_vocab.get(head, 0)]] * (self.relation_input_size - 1) 204 | tails_vec = [[self.tail_vocab.get(tail, 0)]] * (self.relation_input_size - 1) 205 | 206 | feed = { 207 | self.head_inputs:heads_vec, 208 | self.tail_inputs:tails_vec, 209 | self.relation_inputs:relations_vec, 210 | self.dropout:1 211 | } 212 | logits = sess.run(self.logits, feed_dict=feed) 213 | min_index = np.argmin(logits) 214 | print(logits) 215 | print("the relation between {} and {} is {}".format( 216 | head, tail, relations[min_index] 217 | )) 218 | 219 | if __name__ == "__main__": 220 | tr = TransR() 221 | tr.predict_relations("北京大学", "北京") 222 | # tr.train() 223 | --------------------------------------------------------------------------------