├── .gitignore ├── GENIUS_gby_arxiv.pdf ├── README.md ├── _backup_scripts ├── data_prepare.ipynb ├── easy_text_augmenter.py ├── k2t_new_ner_aug.py ├── k2t_new_sm_aug.py ├── model_upload.ipynb ├── my_dataset.py ├── ner_aug.py ├── nlg_eval.ipynb ├── prepare_k2t_data_with_mask.py ├── qa_aug_eda.py ├── qa_back_trans.py ├── run_aug.py ├── run_ner.py ├── run_qa_aug.py ├── s2t_utils.py └── sega_yahoo.py ├── aspect_keybert.py ├── augmentation_clf ├── README.md ├── STA │ ├── .gitignore │ ├── README.md │ ├── __init__.py │ ├── clf.py │ ├── demo.ipynb │ ├── extract-global-keywords.py │ ├── keywords_extractor.py │ ├── my_dataset.py │ ├── run_aug.sh │ ├── run_clf.sh │ ├── run_eda.py │ ├── run_sta.py │ ├── stopwords │ │ ├── en_stopwords.txt │ │ └── zh_stopwords.txt │ ├── text_augmenter.py │ └── utils.py ├── aug_filter_clf.py ├── backtrans_clf.py ├── conditional_clm_clf.py ├── conditional_clm_finetune.py ├── conditional_mlm_clf.py ├── conditional_mlm_finetune.py ├── eda_clf.py ├── genius_clf.py ├── genius_finetune.py ├── genius_mixup_clf.py ├── label_desc.py ├── mlm_clf.py ├── run_aug.sh ├── run_filter.sh ├── sta_clf.py └── sta_extract_kws.py ├── augmentation_ner_qa ├── filter_qa_aug.py ├── genius_ner_aug.py ├── genius_qa_aug.py ├── run_ner.py ├── run_qa.py ├── run_qa.sh ├── trainer_qa.py └── utils_qa.py ├── do_clf.py ├── genius_utils.py ├── pre_training ├── genius_pretrain.py ├── genius_pretrain_chinese.py ├── prepare_genius_pretrain_data.py ├── prepare_genius_pretrain_data_chinese.py └── pretrain.sh ├── utils.py └── yake ├── Levenshtein.py ├── StopwordsList ├── stopwords_en.txt ├── stopwords_fr.txt ├── stopwords_noLang.txt └── stopwords_zh.txt ├── __init__.py ├── cli.py ├── datarepresentation.py ├── highlight.py └── yake.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/.gitignore -------------------------------------------------------------------------------- /GENIUS_gby_arxiv.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/GENIUS_gby_arxiv.pdf -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/README.md -------------------------------------------------------------------------------- /_backup_scripts/data_prepare.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/_backup_scripts/data_prepare.ipynb -------------------------------------------------------------------------------- /_backup_scripts/easy_text_augmenter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/_backup_scripts/easy_text_augmenter.py -------------------------------------------------------------------------------- /_backup_scripts/k2t_new_ner_aug.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/_backup_scripts/k2t_new_ner_aug.py -------------------------------------------------------------------------------- /_backup_scripts/k2t_new_sm_aug.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/_backup_scripts/k2t_new_sm_aug.py -------------------------------------------------------------------------------- /_backup_scripts/model_upload.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/_backup_scripts/model_upload.ipynb -------------------------------------------------------------------------------- /_backup_scripts/my_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/_backup_scripts/my_dataset.py -------------------------------------------------------------------------------- /_backup_scripts/ner_aug.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/_backup_scripts/ner_aug.py -------------------------------------------------------------------------------- /_backup_scripts/nlg_eval.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/_backup_scripts/nlg_eval.ipynb -------------------------------------------------------------------------------- /_backup_scripts/prepare_k2t_data_with_mask.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/_backup_scripts/prepare_k2t_data_with_mask.py -------------------------------------------------------------------------------- /_backup_scripts/qa_aug_eda.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/_backup_scripts/qa_aug_eda.py -------------------------------------------------------------------------------- /_backup_scripts/qa_back_trans.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/_backup_scripts/qa_back_trans.py -------------------------------------------------------------------------------- /_backup_scripts/run_aug.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/_backup_scripts/run_aug.py -------------------------------------------------------------------------------- /_backup_scripts/run_ner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/_backup_scripts/run_ner.py -------------------------------------------------------------------------------- /_backup_scripts/run_qa_aug.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/_backup_scripts/run_qa_aug.py -------------------------------------------------------------------------------- /_backup_scripts/s2t_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/_backup_scripts/s2t_utils.py -------------------------------------------------------------------------------- /_backup_scripts/sega_yahoo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/_backup_scripts/sega_yahoo.py -------------------------------------------------------------------------------- /aspect_keybert.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/aspect_keybert.py -------------------------------------------------------------------------------- /augmentation_clf/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_clf/README.md -------------------------------------------------------------------------------- /augmentation_clf/STA/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_clf/STA/.gitignore -------------------------------------------------------------------------------- /augmentation_clf/STA/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_clf/STA/README.md -------------------------------------------------------------------------------- /augmentation_clf/STA/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /augmentation_clf/STA/clf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_clf/STA/clf.py -------------------------------------------------------------------------------- /augmentation_clf/STA/demo.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_clf/STA/demo.ipynb -------------------------------------------------------------------------------- /augmentation_clf/STA/extract-global-keywords.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_clf/STA/extract-global-keywords.py -------------------------------------------------------------------------------- /augmentation_clf/STA/keywords_extractor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_clf/STA/keywords_extractor.py -------------------------------------------------------------------------------- /augmentation_clf/STA/my_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_clf/STA/my_dataset.py -------------------------------------------------------------------------------- /augmentation_clf/STA/run_aug.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_clf/STA/run_aug.sh -------------------------------------------------------------------------------- /augmentation_clf/STA/run_clf.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_clf/STA/run_clf.sh -------------------------------------------------------------------------------- /augmentation_clf/STA/run_eda.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_clf/STA/run_eda.py -------------------------------------------------------------------------------- /augmentation_clf/STA/run_sta.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_clf/STA/run_sta.py -------------------------------------------------------------------------------- /augmentation_clf/STA/stopwords/en_stopwords.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_clf/STA/stopwords/en_stopwords.txt -------------------------------------------------------------------------------- /augmentation_clf/STA/stopwords/zh_stopwords.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_clf/STA/stopwords/zh_stopwords.txt -------------------------------------------------------------------------------- /augmentation_clf/STA/text_augmenter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_clf/STA/text_augmenter.py -------------------------------------------------------------------------------- /augmentation_clf/STA/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_clf/STA/utils.py -------------------------------------------------------------------------------- /augmentation_clf/aug_filter_clf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_clf/aug_filter_clf.py -------------------------------------------------------------------------------- /augmentation_clf/backtrans_clf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_clf/backtrans_clf.py -------------------------------------------------------------------------------- /augmentation_clf/conditional_clm_clf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_clf/conditional_clm_clf.py -------------------------------------------------------------------------------- /augmentation_clf/conditional_clm_finetune.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_clf/conditional_clm_finetune.py -------------------------------------------------------------------------------- /augmentation_clf/conditional_mlm_clf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_clf/conditional_mlm_clf.py -------------------------------------------------------------------------------- /augmentation_clf/conditional_mlm_finetune.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_clf/conditional_mlm_finetune.py -------------------------------------------------------------------------------- /augmentation_clf/eda_clf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_clf/eda_clf.py -------------------------------------------------------------------------------- /augmentation_clf/genius_clf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_clf/genius_clf.py -------------------------------------------------------------------------------- /augmentation_clf/genius_finetune.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_clf/genius_finetune.py -------------------------------------------------------------------------------- /augmentation_clf/genius_mixup_clf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_clf/genius_mixup_clf.py -------------------------------------------------------------------------------- /augmentation_clf/label_desc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_clf/label_desc.py -------------------------------------------------------------------------------- /augmentation_clf/mlm_clf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_clf/mlm_clf.py -------------------------------------------------------------------------------- /augmentation_clf/run_aug.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_clf/run_aug.sh -------------------------------------------------------------------------------- /augmentation_clf/run_filter.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_clf/run_filter.sh -------------------------------------------------------------------------------- /augmentation_clf/sta_clf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_clf/sta_clf.py -------------------------------------------------------------------------------- /augmentation_clf/sta_extract_kws.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_clf/sta_extract_kws.py -------------------------------------------------------------------------------- /augmentation_ner_qa/filter_qa_aug.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_ner_qa/filter_qa_aug.py -------------------------------------------------------------------------------- /augmentation_ner_qa/genius_ner_aug.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_ner_qa/genius_ner_aug.py -------------------------------------------------------------------------------- /augmentation_ner_qa/genius_qa_aug.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_ner_qa/genius_qa_aug.py -------------------------------------------------------------------------------- /augmentation_ner_qa/run_ner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_ner_qa/run_ner.py -------------------------------------------------------------------------------- /augmentation_ner_qa/run_qa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_ner_qa/run_qa.py -------------------------------------------------------------------------------- /augmentation_ner_qa/run_qa.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_ner_qa/run_qa.sh -------------------------------------------------------------------------------- /augmentation_ner_qa/trainer_qa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_ner_qa/trainer_qa.py -------------------------------------------------------------------------------- /augmentation_ner_qa/utils_qa.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/augmentation_ner_qa/utils_qa.py -------------------------------------------------------------------------------- /do_clf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/do_clf.py -------------------------------------------------------------------------------- /genius_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/genius_utils.py -------------------------------------------------------------------------------- /pre_training/genius_pretrain.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/pre_training/genius_pretrain.py -------------------------------------------------------------------------------- /pre_training/genius_pretrain_chinese.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/pre_training/genius_pretrain_chinese.py -------------------------------------------------------------------------------- /pre_training/prepare_genius_pretrain_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/pre_training/prepare_genius_pretrain_data.py -------------------------------------------------------------------------------- /pre_training/prepare_genius_pretrain_data_chinese.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/pre_training/prepare_genius_pretrain_data_chinese.py -------------------------------------------------------------------------------- /pre_training/pretrain.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/pre_training/pretrain.sh -------------------------------------------------------------------------------- /utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/utils.py -------------------------------------------------------------------------------- /yake/Levenshtein.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/yake/Levenshtein.py -------------------------------------------------------------------------------- /yake/StopwordsList/stopwords_en.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/yake/StopwordsList/stopwords_en.txt -------------------------------------------------------------------------------- /yake/StopwordsList/stopwords_fr.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/yake/StopwordsList/stopwords_fr.txt -------------------------------------------------------------------------------- /yake/StopwordsList/stopwords_noLang.txt: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /yake/StopwordsList/stopwords_zh.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/yake/StopwordsList/stopwords_zh.txt -------------------------------------------------------------------------------- /yake/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/yake/__init__.py -------------------------------------------------------------------------------- /yake/cli.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/yake/cli.py -------------------------------------------------------------------------------- /yake/datarepresentation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/yake/datarepresentation.py -------------------------------------------------------------------------------- /yake/highlight.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/yake/highlight.py -------------------------------------------------------------------------------- /yake/yake.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/beyondguo/genius/HEAD/yake/yake.py --------------------------------------------------------------------------------