├── .gitignore ├── README.md ├── code_evaluation ├── task1 │ ├── RobertaWithSampleWeight.py │ ├── RobertaWithSampleWeight_EmbBag.py │ ├── run_embbag.py │ ├── run_origin.py │ └── utils.py ├── task2 │ ├── run.py │ └── run_embbag.py └── task3 │ └── run.py ├── code_postprocess ├── CAN.py └── README.md ├── code_preprocess ├── 1_query_hash.py ├── 3_create_pretrain_data.py ├── 3_create_pretrain_data_brand_color.py ├── 4_translation_es_us.py ├── 5_tokenizer_n-gram.py ├── 6_rebalance_negative_samples.py ├── 7_confidient_learning_filter.py ├── README.md ├── data_analysis │ ├── brand_color_analysis.py │ ├── language_analysis.py │ ├── query_analysis.py │ ├── task1_task2_diff.py │ ├── title_analysis.py │ └── tokenizer_len_analysis.py └── word2vec │ ├── data_process.py │ ├── test_w2v_sim.py │ └── train_skipgram.py ├── code_pretrain ├── README.md ├── multi_task_model.py ├── parameter.py ├── run_mlm_no_trainer_multi_task.py ├── run_mlm_no_trainer_multi_task_contrasitive.py ├── run_mlm_no_trainer_multi_task_extra_embedding.py ├── run_train_pretrain_multi_task.sh └── utils.py ├── code_task1 ├── RobertaWithSampleWeight.py ├── RobertaWithSampleWeight_Bag.py ├── parameter.py ├── run_glue_no_trainer.py ├── run_glue_no_trainer_Bag.py ├── run_train.sh └── utils.py ├── code_task2 ├── RobertaWithSampleWeight_Bag.py ├── RobertaWithSampleWeight_Moe.py ├── RobertaWithSampleWeight_doubletower.py ├── parameter.py ├── run_glue_no_trainer.py ├── run_glue_no_trainer_bag.py ├── run_glue_no_trainer_doubletower.py ├── run_train.sh └── utils.py ├── code_task3 ├── RobertaWithSampleWeight.py ├── parameter.py ├── run_glue_no_trainer.py ├── run_train.sh └── utils.py ├── paper ├── Review_ZhichunRoad_20220730.pdf └── poster_presentation.png └── requirements.txt /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/.gitignore -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/README.md -------------------------------------------------------------------------------- /code_evaluation/task1/RobertaWithSampleWeight.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_evaluation/task1/RobertaWithSampleWeight.py -------------------------------------------------------------------------------- /code_evaluation/task1/RobertaWithSampleWeight_EmbBag.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_evaluation/task1/RobertaWithSampleWeight_EmbBag.py -------------------------------------------------------------------------------- /code_evaluation/task1/run_embbag.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_evaluation/task1/run_embbag.py -------------------------------------------------------------------------------- /code_evaluation/task1/run_origin.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_evaluation/task1/run_origin.py -------------------------------------------------------------------------------- /code_evaluation/task1/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_evaluation/task1/utils.py -------------------------------------------------------------------------------- /code_evaluation/task2/run.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_evaluation/task2/run.py -------------------------------------------------------------------------------- /code_evaluation/task2/run_embbag.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_evaluation/task2/run_embbag.py -------------------------------------------------------------------------------- /code_evaluation/task3/run.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_evaluation/task3/run.py -------------------------------------------------------------------------------- /code_postprocess/CAN.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_postprocess/CAN.py -------------------------------------------------------------------------------- /code_postprocess/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_postprocess/README.md -------------------------------------------------------------------------------- /code_preprocess/1_query_hash.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_preprocess/1_query_hash.py -------------------------------------------------------------------------------- /code_preprocess/3_create_pretrain_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_preprocess/3_create_pretrain_data.py -------------------------------------------------------------------------------- /code_preprocess/3_create_pretrain_data_brand_color.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_preprocess/3_create_pretrain_data_brand_color.py -------------------------------------------------------------------------------- /code_preprocess/4_translation_es_us.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_preprocess/4_translation_es_us.py -------------------------------------------------------------------------------- /code_preprocess/5_tokenizer_n-gram.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_preprocess/5_tokenizer_n-gram.py -------------------------------------------------------------------------------- /code_preprocess/6_rebalance_negative_samples.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_preprocess/6_rebalance_negative_samples.py -------------------------------------------------------------------------------- /code_preprocess/7_confidient_learning_filter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_preprocess/7_confidient_learning_filter.py -------------------------------------------------------------------------------- /code_preprocess/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_preprocess/README.md -------------------------------------------------------------------------------- /code_preprocess/data_analysis/brand_color_analysis.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_preprocess/data_analysis/brand_color_analysis.py -------------------------------------------------------------------------------- /code_preprocess/data_analysis/language_analysis.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_preprocess/data_analysis/language_analysis.py -------------------------------------------------------------------------------- /code_preprocess/data_analysis/query_analysis.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_preprocess/data_analysis/query_analysis.py -------------------------------------------------------------------------------- /code_preprocess/data_analysis/task1_task2_diff.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_preprocess/data_analysis/task1_task2_diff.py -------------------------------------------------------------------------------- /code_preprocess/data_analysis/title_analysis.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_preprocess/data_analysis/title_analysis.py -------------------------------------------------------------------------------- /code_preprocess/data_analysis/tokenizer_len_analysis.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_preprocess/data_analysis/tokenizer_len_analysis.py -------------------------------------------------------------------------------- /code_preprocess/word2vec/data_process.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_preprocess/word2vec/data_process.py -------------------------------------------------------------------------------- /code_preprocess/word2vec/test_w2v_sim.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_preprocess/word2vec/test_w2v_sim.py -------------------------------------------------------------------------------- /code_preprocess/word2vec/train_skipgram.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_preprocess/word2vec/train_skipgram.py -------------------------------------------------------------------------------- /code_pretrain/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_pretrain/README.md -------------------------------------------------------------------------------- /code_pretrain/multi_task_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_pretrain/multi_task_model.py -------------------------------------------------------------------------------- /code_pretrain/parameter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_pretrain/parameter.py -------------------------------------------------------------------------------- /code_pretrain/run_mlm_no_trainer_multi_task.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_pretrain/run_mlm_no_trainer_multi_task.py -------------------------------------------------------------------------------- /code_pretrain/run_mlm_no_trainer_multi_task_contrasitive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_pretrain/run_mlm_no_trainer_multi_task_contrasitive.py -------------------------------------------------------------------------------- /code_pretrain/run_mlm_no_trainer_multi_task_extra_embedding.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_pretrain/run_mlm_no_trainer_multi_task_extra_embedding.py -------------------------------------------------------------------------------- /code_pretrain/run_train_pretrain_multi_task.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_pretrain/run_train_pretrain_multi_task.sh -------------------------------------------------------------------------------- /code_pretrain/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_pretrain/utils.py -------------------------------------------------------------------------------- /code_task1/RobertaWithSampleWeight.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_task1/RobertaWithSampleWeight.py -------------------------------------------------------------------------------- /code_task1/RobertaWithSampleWeight_Bag.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_task1/RobertaWithSampleWeight_Bag.py -------------------------------------------------------------------------------- /code_task1/parameter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_task1/parameter.py -------------------------------------------------------------------------------- /code_task1/run_glue_no_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_task1/run_glue_no_trainer.py -------------------------------------------------------------------------------- /code_task1/run_glue_no_trainer_Bag.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_task1/run_glue_no_trainer_Bag.py -------------------------------------------------------------------------------- /code_task1/run_train.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_task1/run_train.sh -------------------------------------------------------------------------------- /code_task1/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_task1/utils.py -------------------------------------------------------------------------------- /code_task2/RobertaWithSampleWeight_Bag.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_task2/RobertaWithSampleWeight_Bag.py -------------------------------------------------------------------------------- /code_task2/RobertaWithSampleWeight_Moe.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_task2/RobertaWithSampleWeight_Moe.py -------------------------------------------------------------------------------- /code_task2/RobertaWithSampleWeight_doubletower.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_task2/RobertaWithSampleWeight_doubletower.py -------------------------------------------------------------------------------- /code_task2/parameter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_task2/parameter.py -------------------------------------------------------------------------------- /code_task2/run_glue_no_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_task2/run_glue_no_trainer.py -------------------------------------------------------------------------------- /code_task2/run_glue_no_trainer_bag.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_task2/run_glue_no_trainer_bag.py -------------------------------------------------------------------------------- /code_task2/run_glue_no_trainer_doubletower.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_task2/run_glue_no_trainer_doubletower.py -------------------------------------------------------------------------------- /code_task2/run_train.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_task2/run_train.sh -------------------------------------------------------------------------------- /code_task2/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_task2/utils.py -------------------------------------------------------------------------------- /code_task3/RobertaWithSampleWeight.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_task3/RobertaWithSampleWeight.py -------------------------------------------------------------------------------- /code_task3/parameter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_task3/parameter.py -------------------------------------------------------------------------------- /code_task3/run_glue_no_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_task3/run_glue_no_trainer.py -------------------------------------------------------------------------------- /code_task3/run_train.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_task3/run_train.sh -------------------------------------------------------------------------------- /code_task3/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/code_task3/utils.py -------------------------------------------------------------------------------- /paper/Review_ZhichunRoad_20220730.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/paper/Review_ZhichunRoad_20220730.pdf -------------------------------------------------------------------------------- /paper/poster_presentation.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/paper/poster_presentation.png -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/cuixuage/KDDCup2022-ESCI/HEAD/requirements.txt --------------------------------------------------------------------------------