├── .gitignore ├── LICENSE ├── README.md ├── action-item-detection ├── README.md ├── data │ └── AMI │ │ ├── ami_public_manual_1.6.2 │ │ └── readme.txt │ │ └── similarity │ │ └── similarity_ngram_cosine_ami101a.json ├── data_script │ └── ami_process.py └── script │ ├── LICENSE │ ├── NOTICE │ ├── __init__.py │ ├── average_performance.py │ ├── create_pretraining_data.py │ ├── extract_features.py │ ├── go_predict.sh │ ├── go_train.sh │ ├── modeling.py │ ├── modeling_test.py │ ├── night_listener.py │ ├── optimization.py │ ├── optimization_test.py │ ├── repeat_models.sh │ ├── requirements.txt │ ├── run_classifier.py │ ├── run_classifier_with_tfhub.py │ ├── run_pretraining.py │ ├── run_squad.py │ ├── tokenization.py │ └── tokenization_test.py ├── alimeeting4mug ├── image │ ├── dingding.png │ └── sdk_token.png ├── metrics │ ├── classification │ │ ├── __init__.py │ │ └── classification.py │ ├── extractive_summarization_eval │ │ ├── __init__.py │ │ └── extractive_summarization_eval.py │ ├── keyphrase_extraction_eval │ │ └── keyphrase_extraction_eval.py │ ├── rouge │ │ ├── __init__.py │ │ └── rouge.py │ └── topic_seg_eval │ │ ├── __init__.py │ │ └── topic_seg_eval.py ├── readme.md ├── requirements.txt ├── run_palm_topic_title_generation.sh ├── run_ponet_doc_extractive_summarization.sh ├── run_ponet_topic_extractive_summarization.sh ├── run_ponet_topic_segmentation.sh ├── run_structbert_action_item_detection.sh ├── src │ ├── action_item_detection │ │ ├── structbert_meeting_action.py │ │ └── submit_file_generation.py │ ├── extractive_summarization │ │ ├── ponet_extractive_summarization.py │ │ └── submit_file_generation.py │ ├── keyphrase_extraction │ │ └── README.md │ ├── models │ │ ├── __init__.py │ │ ├── modeling_ponet.py │ │ └── trainer.py │ ├── topic_segment │ │ ├── ponet_topic_segmentation.py │ │ └── submit_file_generation.py │ ├── topic_title_generation │ │ ├── palm_subtitle_generation.py │ │ └── submit_file_generation.py │ └── utils │ │ ├── __init__.py │ │ ├── challenge_evaluate.py │ │ ├── config.py │ │ ├── extractive_summarization_submit_file_generation.py │ │ ├── tokenizer.py │ │ └── tokenizer_utils.py └── submitted_samples │ ├── action_item_detection_dev_pesudo_submit.json │ ├── extractive_summarization_dev_pesudo_submit.json │ ├── keyphrase_extraction_dev_pesudo_submit.json │ ├── topic_segmentation_dev_pesudo_submit.json │ └── topic_title_generation_dev_pesudo_submit.json ├── ditto ├── .gitignore ├── LICENSE ├── README.md ├── SentEval │ ├── .gitignore │ ├── LICENSE │ ├── README.md │ ├── data │ │ └── downstream │ │ │ └── download_dataset.sh │ ├── examples │ │ ├── bow.py │ │ ├── gensen.py │ │ ├── googleuse.py │ │ ├── infersent.py │ │ ├── models.py │ │ └── skipthought.py │ ├── senteval │ │ ├── __init__.py │ │ ├── binary.py │ │ ├── engine.py │ │ ├── mrpc.py │ │ ├── probing.py │ │ ├── rank.py │ │ ├── sick.py │ │ ├── snli.py │ │ ├── sst.py │ │ ├── sts.py │ │ ├── tools │ │ │ ├── __init__.py │ │ │ ├── classifier.py │ │ │ ├── ranking.py │ │ │ ├── relatedness.py │ │ │ └── validation.py │ │ ├── trec.py │ │ └── utils.py │ └── setup.py ├── evaluation_ditto.py ├── figure │ └── ditto.png ├── requirements.txt └── run_eval_ditto.sh ├── emnlp2023-topic_segmentation ├── .ignore ├── README.md ├── config │ └── config.ini ├── requirements.txt ├── run_finetune.sh ├── run_inference.sh ├── run_process_data.sh └── src │ ├── __init__.py │ ├── __pycache__ │ ├── arguments.cpython-38.pyc │ └── utils.cpython-38.pyc │ ├── analysis │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-38.pyc │ │ ├── statistics_of_data.cpython-38.pyc │ │ ├── tokenizer.cpython-38.pyc │ │ └── tokenizer_utils.cpython-38.pyc │ ├── ensemble_scores.py │ ├── plot_figure.py │ ├── statistics_of_data.py │ ├── statistics_of_result.py │ ├── tokenizer.py │ └── tokenizer_utils.py │ ├── arguments.py │ ├── datasets │ ├── wiki50 │ │ └── wiki50.py │ ├── wiki727k │ │ └── wiki727k.py │ ├── wiki_elements │ │ └── wiki_elements.py │ ├── wiki_section │ │ └── wiki_section.py │ ├── wiki_section_city │ │ └── wiki_section_city.py │ └── wiki_section_disease │ │ └── wiki_section_disease.py │ ├── metrics │ ├── __init__.py │ └── seqeval.py │ ├── models │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-38.pyc │ │ └── longformer_for_ts.cpython-38.pyc │ ├── bert_for_ts.py │ ├── bigbird_for_ts.py │ ├── electra_for_ts.py │ ├── longformer_for_ts.py │ └── modules │ │ ├── __init__.py │ │ ├── __pycache__ │ │ ├── __init__.cpython-38.pyc │ │ ├── cssl.cpython-38.pyc │ │ ├── loss_calculator.cpython-38.pyc │ │ ├── tssp.cpython-38.pyc │ │ └── utils.cpython-38.pyc │ │ ├── cssl.py │ │ ├── loss_calculator.py │ │ ├── tssp.py │ │ └── utils.py │ ├── postprocess_predictions.py │ ├── preprocess_data.py │ ├── ts_sentence_seq_labeling.py │ └── utils.py ├── mmvts ├── README.md ├── data │ ├── avlecture │ │ ├── .DS_Store │ │ ├── dev.jsonl │ │ ├── test.jsonl │ │ └── train.jsonl │ └── clvts │ │ ├── .DS_Store │ │ ├── dev.jsonl │ │ ├── test.jsonl │ │ └── train.jsonl ├── run_finetune_multimodal.sh ├── run_finetune_text.sh └── src │ ├── arguments.py │ ├── datasets │ ├── avlecture │ │ └── avlecture.py │ └── clvts │ │ └── clvts.py │ ├── evaluate.py │ ├── main_multimodal.py │ ├── main_text.py │ ├── metrics │ ├── __init__.py │ └── seqeval.py │ ├── models │ ├── __init__.py │ ├── audio_encoder │ │ └── audio_encoder.py │ ├── cross_encoder │ │ ├── bert_model.py │ │ ├── ca_encoder.py │ │ ├── ca_moe_encoder.py │ │ ├── get_cross_encoder.py │ │ ├── ma_encoder.py │ │ ├── ma_moe_encoder.py │ │ └── moe.py │ ├── modules │ │ ├── __init__.py │ │ ├── contrastive_learning_layer.py │ │ ├── gated_fusion.py │ │ └── loss_layer.py │ ├── multi_modal_for_ts.py │ ├── predictor │ │ ├── __init__.py │ │ ├── base_predictor.py │ │ ├── hybrid_predictor.py │ │ ├── linear_predictor.py │ │ ├── topic_seg_predictor.py │ │ └── transformer_predictor.py │ ├── projector │ │ ├── get_projector.py │ │ ├── linear_projector.py │ │ └── transformer_projector.py │ ├── text_encoder │ │ ├── __init__.py │ │ └── text_encoder.py │ ├── utils.py │ └── vis_encoder │ │ ├── __init__.py │ │ ├── clip │ │ ├── __init__.py │ │ ├── bpe_simple_vocab_16e6.txt.gz │ │ ├── clip.py │ │ ├── model.py │ │ └── simple_tokenizer.py │ │ ├── vis2d_encoder.py │ │ ├── vis3d_encoder.py │ │ ├── vis_encoder.py │ │ └── vis_ocr_encoder.py │ ├── pretrain.py │ ├── requirements.txt │ └── utils.py ├── sld ├── .gitignore ├── README.md ├── fairseq │ └── examples │ │ ├── hubert │ │ └── simple_kmeans │ │ │ ├── WavLM.py │ │ │ ├── dump_hubert_feature.py │ │ │ ├── dump_km.py │ │ │ ├── dump_wavlm_feature.py │ │ │ ├── feature_utils.py │ │ │ ├── learn_kmeans.py │ │ │ └── modules.py │ │ └── wav2vec │ │ ├── libri_labels.py │ │ └── wav2vec_manifest.py ├── figure │ └── sld.png ├── requirements.txt ├── run.sh ├── transformers │ └── examples │ │ └── pytorch │ │ └── language-modeling │ │ └── run_clm.py └── utils │ ├── cer │ └── cer.py │ ├── line_to_json.py │ ├── run_sentencepiece.py │ └── wer │ └── wer.py └── swab ├── README.md └── example └── swab_example.json /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/README.md -------------------------------------------------------------------------------- /action-item-detection/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/action-item-detection/README.md -------------------------------------------------------------------------------- /action-item-detection/data/AMI/ami_public_manual_1.6.2/readme.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/action-item-detection/data/AMI/ami_public_manual_1.6.2/readme.txt -------------------------------------------------------------------------------- /action-item-detection/data/AMI/similarity/similarity_ngram_cosine_ami101a.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/action-item-detection/data/AMI/similarity/similarity_ngram_cosine_ami101a.json -------------------------------------------------------------------------------- /action-item-detection/data_script/ami_process.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/action-item-detection/data_script/ami_process.py -------------------------------------------------------------------------------- /action-item-detection/script/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/action-item-detection/script/LICENSE -------------------------------------------------------------------------------- /action-item-detection/script/NOTICE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/action-item-detection/script/NOTICE -------------------------------------------------------------------------------- /action-item-detection/script/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/action-item-detection/script/__init__.py -------------------------------------------------------------------------------- /action-item-detection/script/average_performance.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/action-item-detection/script/average_performance.py -------------------------------------------------------------------------------- /action-item-detection/script/create_pretraining_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/action-item-detection/script/create_pretraining_data.py -------------------------------------------------------------------------------- /action-item-detection/script/extract_features.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/action-item-detection/script/extract_features.py -------------------------------------------------------------------------------- /action-item-detection/script/go_predict.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/action-item-detection/script/go_predict.sh -------------------------------------------------------------------------------- /action-item-detection/script/go_train.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/action-item-detection/script/go_train.sh -------------------------------------------------------------------------------- /action-item-detection/script/modeling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/action-item-detection/script/modeling.py -------------------------------------------------------------------------------- /action-item-detection/script/modeling_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/action-item-detection/script/modeling_test.py -------------------------------------------------------------------------------- /action-item-detection/script/night_listener.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/action-item-detection/script/night_listener.py -------------------------------------------------------------------------------- /action-item-detection/script/optimization.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/action-item-detection/script/optimization.py -------------------------------------------------------------------------------- /action-item-detection/script/optimization_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/action-item-detection/script/optimization_test.py -------------------------------------------------------------------------------- /action-item-detection/script/repeat_models.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/action-item-detection/script/repeat_models.sh -------------------------------------------------------------------------------- /action-item-detection/script/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/action-item-detection/script/requirements.txt -------------------------------------------------------------------------------- /action-item-detection/script/run_classifier.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/action-item-detection/script/run_classifier.py -------------------------------------------------------------------------------- /action-item-detection/script/run_classifier_with_tfhub.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/action-item-detection/script/run_classifier_with_tfhub.py -------------------------------------------------------------------------------- /action-item-detection/script/run_pretraining.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/action-item-detection/script/run_pretraining.py -------------------------------------------------------------------------------- /action-item-detection/script/run_squad.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/action-item-detection/script/run_squad.py -------------------------------------------------------------------------------- /action-item-detection/script/tokenization.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/action-item-detection/script/tokenization.py -------------------------------------------------------------------------------- /action-item-detection/script/tokenization_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/action-item-detection/script/tokenization_test.py -------------------------------------------------------------------------------- /alimeeting4mug/image/dingding.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/alimeeting4mug/image/dingding.png -------------------------------------------------------------------------------- /alimeeting4mug/image/sdk_token.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/alimeeting4mug/image/sdk_token.png -------------------------------------------------------------------------------- /alimeeting4mug/metrics/classification/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /alimeeting4mug/metrics/classification/classification.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/alimeeting4mug/metrics/classification/classification.py -------------------------------------------------------------------------------- /alimeeting4mug/metrics/extractive_summarization_eval/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /alimeeting4mug/metrics/extractive_summarization_eval/extractive_summarization_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/alimeeting4mug/metrics/extractive_summarization_eval/extractive_summarization_eval.py -------------------------------------------------------------------------------- /alimeeting4mug/metrics/keyphrase_extraction_eval/keyphrase_extraction_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/alimeeting4mug/metrics/keyphrase_extraction_eval/keyphrase_extraction_eval.py -------------------------------------------------------------------------------- /alimeeting4mug/metrics/rouge/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /alimeeting4mug/metrics/rouge/rouge.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/alimeeting4mug/metrics/rouge/rouge.py -------------------------------------------------------------------------------- /alimeeting4mug/metrics/topic_seg_eval/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /alimeeting4mug/metrics/topic_seg_eval/topic_seg_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/alimeeting4mug/metrics/topic_seg_eval/topic_seg_eval.py -------------------------------------------------------------------------------- /alimeeting4mug/readme.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/alimeeting4mug/readme.md -------------------------------------------------------------------------------- /alimeeting4mug/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/alimeeting4mug/requirements.txt -------------------------------------------------------------------------------- /alimeeting4mug/run_palm_topic_title_generation.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/alimeeting4mug/run_palm_topic_title_generation.sh -------------------------------------------------------------------------------- /alimeeting4mug/run_ponet_doc_extractive_summarization.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/alimeeting4mug/run_ponet_doc_extractive_summarization.sh -------------------------------------------------------------------------------- /alimeeting4mug/run_ponet_topic_extractive_summarization.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/alimeeting4mug/run_ponet_topic_extractive_summarization.sh -------------------------------------------------------------------------------- /alimeeting4mug/run_ponet_topic_segmentation.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/alimeeting4mug/run_ponet_topic_segmentation.sh -------------------------------------------------------------------------------- /alimeeting4mug/run_structbert_action_item_detection.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/alimeeting4mug/run_structbert_action_item_detection.sh -------------------------------------------------------------------------------- /alimeeting4mug/src/action_item_detection/structbert_meeting_action.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/alimeeting4mug/src/action_item_detection/structbert_meeting_action.py -------------------------------------------------------------------------------- /alimeeting4mug/src/action_item_detection/submit_file_generation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/alimeeting4mug/src/action_item_detection/submit_file_generation.py -------------------------------------------------------------------------------- /alimeeting4mug/src/extractive_summarization/ponet_extractive_summarization.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/alimeeting4mug/src/extractive_summarization/ponet_extractive_summarization.py -------------------------------------------------------------------------------- /alimeeting4mug/src/extractive_summarization/submit_file_generation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/alimeeting4mug/src/extractive_summarization/submit_file_generation.py -------------------------------------------------------------------------------- /alimeeting4mug/src/keyphrase_extraction/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/alimeeting4mug/src/keyphrase_extraction/README.md -------------------------------------------------------------------------------- /alimeeting4mug/src/models/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /alimeeting4mug/src/models/modeling_ponet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/alimeeting4mug/src/models/modeling_ponet.py -------------------------------------------------------------------------------- /alimeeting4mug/src/models/trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/alimeeting4mug/src/models/trainer.py -------------------------------------------------------------------------------- /alimeeting4mug/src/topic_segment/ponet_topic_segmentation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/alimeeting4mug/src/topic_segment/ponet_topic_segmentation.py -------------------------------------------------------------------------------- /alimeeting4mug/src/topic_segment/submit_file_generation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/alimeeting4mug/src/topic_segment/submit_file_generation.py -------------------------------------------------------------------------------- /alimeeting4mug/src/topic_title_generation/palm_subtitle_generation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/alimeeting4mug/src/topic_title_generation/palm_subtitle_generation.py -------------------------------------------------------------------------------- /alimeeting4mug/src/topic_title_generation/submit_file_generation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/alimeeting4mug/src/topic_title_generation/submit_file_generation.py -------------------------------------------------------------------------------- /alimeeting4mug/src/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /alimeeting4mug/src/utils/challenge_evaluate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/alimeeting4mug/src/utils/challenge_evaluate.py -------------------------------------------------------------------------------- /alimeeting4mug/src/utils/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/alimeeting4mug/src/utils/config.py -------------------------------------------------------------------------------- /alimeeting4mug/src/utils/extractive_summarization_submit_file_generation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/alimeeting4mug/src/utils/extractive_summarization_submit_file_generation.py -------------------------------------------------------------------------------- /alimeeting4mug/src/utils/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/alimeeting4mug/src/utils/tokenizer.py -------------------------------------------------------------------------------- /alimeeting4mug/src/utils/tokenizer_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/alimeeting4mug/src/utils/tokenizer_utils.py -------------------------------------------------------------------------------- /alimeeting4mug/submitted_samples/action_item_detection_dev_pesudo_submit.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/alimeeting4mug/submitted_samples/action_item_detection_dev_pesudo_submit.json -------------------------------------------------------------------------------- /alimeeting4mug/submitted_samples/extractive_summarization_dev_pesudo_submit.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/alimeeting4mug/submitted_samples/extractive_summarization_dev_pesudo_submit.json -------------------------------------------------------------------------------- /alimeeting4mug/submitted_samples/keyphrase_extraction_dev_pesudo_submit.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/alimeeting4mug/submitted_samples/keyphrase_extraction_dev_pesudo_submit.json -------------------------------------------------------------------------------- /alimeeting4mug/submitted_samples/topic_segmentation_dev_pesudo_submit.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/alimeeting4mug/submitted_samples/topic_segmentation_dev_pesudo_submit.json -------------------------------------------------------------------------------- /alimeeting4mug/submitted_samples/topic_title_generation_dev_pesudo_submit.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/alimeeting4mug/submitted_samples/topic_title_generation_dev_pesudo_submit.json -------------------------------------------------------------------------------- /ditto/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/ditto/.gitignore -------------------------------------------------------------------------------- /ditto/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/ditto/LICENSE -------------------------------------------------------------------------------- /ditto/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/ditto/README.md -------------------------------------------------------------------------------- /ditto/SentEval/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/ditto/SentEval/.gitignore -------------------------------------------------------------------------------- /ditto/SentEval/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/ditto/SentEval/LICENSE -------------------------------------------------------------------------------- /ditto/SentEval/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/ditto/SentEval/README.md -------------------------------------------------------------------------------- /ditto/SentEval/data/downstream/download_dataset.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/ditto/SentEval/data/downstream/download_dataset.sh -------------------------------------------------------------------------------- /ditto/SentEval/examples/bow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/ditto/SentEval/examples/bow.py -------------------------------------------------------------------------------- /ditto/SentEval/examples/gensen.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/ditto/SentEval/examples/gensen.py -------------------------------------------------------------------------------- /ditto/SentEval/examples/googleuse.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/ditto/SentEval/examples/googleuse.py -------------------------------------------------------------------------------- /ditto/SentEval/examples/infersent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/ditto/SentEval/examples/infersent.py -------------------------------------------------------------------------------- /ditto/SentEval/examples/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/ditto/SentEval/examples/models.py -------------------------------------------------------------------------------- /ditto/SentEval/examples/skipthought.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/ditto/SentEval/examples/skipthought.py -------------------------------------------------------------------------------- /ditto/SentEval/senteval/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/ditto/SentEval/senteval/__init__.py -------------------------------------------------------------------------------- /ditto/SentEval/senteval/binary.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/ditto/SentEval/senteval/binary.py -------------------------------------------------------------------------------- /ditto/SentEval/senteval/engine.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/ditto/SentEval/senteval/engine.py -------------------------------------------------------------------------------- /ditto/SentEval/senteval/mrpc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/ditto/SentEval/senteval/mrpc.py -------------------------------------------------------------------------------- /ditto/SentEval/senteval/probing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/ditto/SentEval/senteval/probing.py -------------------------------------------------------------------------------- /ditto/SentEval/senteval/rank.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/ditto/SentEval/senteval/rank.py -------------------------------------------------------------------------------- /ditto/SentEval/senteval/sick.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/ditto/SentEval/senteval/sick.py -------------------------------------------------------------------------------- /ditto/SentEval/senteval/snli.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/ditto/SentEval/senteval/snli.py -------------------------------------------------------------------------------- /ditto/SentEval/senteval/sst.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/ditto/SentEval/senteval/sst.py -------------------------------------------------------------------------------- /ditto/SentEval/senteval/sts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/ditto/SentEval/senteval/sts.py -------------------------------------------------------------------------------- /ditto/SentEval/senteval/tools/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /ditto/SentEval/senteval/tools/classifier.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/ditto/SentEval/senteval/tools/classifier.py -------------------------------------------------------------------------------- /ditto/SentEval/senteval/tools/ranking.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/ditto/SentEval/senteval/tools/ranking.py -------------------------------------------------------------------------------- /ditto/SentEval/senteval/tools/relatedness.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/ditto/SentEval/senteval/tools/relatedness.py -------------------------------------------------------------------------------- /ditto/SentEval/senteval/tools/validation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/ditto/SentEval/senteval/tools/validation.py -------------------------------------------------------------------------------- /ditto/SentEval/senteval/trec.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/ditto/SentEval/senteval/trec.py -------------------------------------------------------------------------------- /ditto/SentEval/senteval/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/ditto/SentEval/senteval/utils.py -------------------------------------------------------------------------------- /ditto/SentEval/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/ditto/SentEval/setup.py -------------------------------------------------------------------------------- /ditto/evaluation_ditto.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/ditto/evaluation_ditto.py -------------------------------------------------------------------------------- /ditto/figure/ditto.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/ditto/figure/ditto.png -------------------------------------------------------------------------------- /ditto/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/ditto/requirements.txt -------------------------------------------------------------------------------- /ditto/run_eval_ditto.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/ditto/run_eval_ditto.sh -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/.ignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/.ignore -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/README.md -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/config/config.ini: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/config/config.ini -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/requirements.txt -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/run_finetune.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/run_finetune.sh -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/run_inference.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/run_inference.sh -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/run_process_data.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/run_process_data.sh -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/__pycache__/arguments.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/__pycache__/arguments.cpython-38.pyc -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/__pycache__/utils.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/__pycache__/utils.cpython-38.pyc -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/analysis/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/analysis/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/analysis/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/analysis/__pycache__/statistics_of_data.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/analysis/__pycache__/statistics_of_data.cpython-38.pyc -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/analysis/__pycache__/tokenizer.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/analysis/__pycache__/tokenizer.cpython-38.pyc -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/analysis/__pycache__/tokenizer_utils.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/analysis/__pycache__/tokenizer_utils.cpython-38.pyc -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/analysis/ensemble_scores.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/analysis/ensemble_scores.py -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/analysis/plot_figure.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/analysis/plot_figure.py -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/analysis/statistics_of_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/analysis/statistics_of_data.py -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/analysis/statistics_of_result.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/analysis/statistics_of_result.py -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/analysis/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/analysis/tokenizer.py -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/analysis/tokenizer_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/analysis/tokenizer_utils.py -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/arguments.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/arguments.py -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/datasets/wiki50/wiki50.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/datasets/wiki50/wiki50.py -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/datasets/wiki727k/wiki727k.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/datasets/wiki727k/wiki727k.py -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/datasets/wiki_elements/wiki_elements.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/datasets/wiki_elements/wiki_elements.py -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/datasets/wiki_section/wiki_section.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/datasets/wiki_section/wiki_section.py -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/datasets/wiki_section_city/wiki_section_city.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/datasets/wiki_section_city/wiki_section_city.py -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/datasets/wiki_section_disease/wiki_section_disease.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/datasets/wiki_section_disease/wiki_section_disease.py -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/metrics/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/metrics/seqeval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/metrics/seqeval.py -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/models/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/models/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/models/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/models/__pycache__/longformer_for_ts.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/models/__pycache__/longformer_for_ts.cpython-38.pyc -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/models/bert_for_ts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/models/bert_for_ts.py -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/models/bigbird_for_ts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/models/bigbird_for_ts.py -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/models/electra_for_ts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/models/electra_for_ts.py -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/models/longformer_for_ts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/models/longformer_for_ts.py -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/models/modules/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/models/modules/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/models/modules/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/models/modules/__pycache__/cssl.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/models/modules/__pycache__/cssl.cpython-38.pyc -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/models/modules/__pycache__/loss_calculator.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/models/modules/__pycache__/loss_calculator.cpython-38.pyc -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/models/modules/__pycache__/tssp.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/models/modules/__pycache__/tssp.cpython-38.pyc -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/models/modules/__pycache__/utils.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/models/modules/__pycache__/utils.cpython-38.pyc -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/models/modules/cssl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/models/modules/cssl.py -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/models/modules/loss_calculator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/models/modules/loss_calculator.py -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/models/modules/tssp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/models/modules/tssp.py -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/models/modules/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/models/modules/utils.py -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/postprocess_predictions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/postprocess_predictions.py -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/preprocess_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/preprocess_data.py -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/ts_sentence_seq_labeling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/ts_sentence_seq_labeling.py -------------------------------------------------------------------------------- /emnlp2023-topic_segmentation/src/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/emnlp2023-topic_segmentation/src/utils.py -------------------------------------------------------------------------------- /mmvts/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/README.md -------------------------------------------------------------------------------- /mmvts/data/avlecture/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/data/avlecture/.DS_Store -------------------------------------------------------------------------------- /mmvts/data/avlecture/dev.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/data/avlecture/dev.jsonl -------------------------------------------------------------------------------- /mmvts/data/avlecture/test.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/data/avlecture/test.jsonl -------------------------------------------------------------------------------- /mmvts/data/avlecture/train.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/data/avlecture/train.jsonl -------------------------------------------------------------------------------- /mmvts/data/clvts/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/data/clvts/.DS_Store -------------------------------------------------------------------------------- /mmvts/data/clvts/dev.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/data/clvts/dev.jsonl -------------------------------------------------------------------------------- /mmvts/data/clvts/test.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/data/clvts/test.jsonl -------------------------------------------------------------------------------- /mmvts/data/clvts/train.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/data/clvts/train.jsonl -------------------------------------------------------------------------------- /mmvts/run_finetune_multimodal.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/run_finetune_multimodal.sh -------------------------------------------------------------------------------- /mmvts/run_finetune_text.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/run_finetune_text.sh -------------------------------------------------------------------------------- /mmvts/src/arguments.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/arguments.py -------------------------------------------------------------------------------- /mmvts/src/datasets/avlecture/avlecture.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/datasets/avlecture/avlecture.py -------------------------------------------------------------------------------- /mmvts/src/datasets/clvts/clvts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/datasets/clvts/clvts.py -------------------------------------------------------------------------------- /mmvts/src/evaluate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/evaluate.py -------------------------------------------------------------------------------- /mmvts/src/main_multimodal.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/main_multimodal.py -------------------------------------------------------------------------------- /mmvts/src/main_text.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/main_text.py -------------------------------------------------------------------------------- /mmvts/src/metrics/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mmvts/src/metrics/seqeval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/metrics/seqeval.py -------------------------------------------------------------------------------- /mmvts/src/models/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mmvts/src/models/audio_encoder/audio_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/models/audio_encoder/audio_encoder.py -------------------------------------------------------------------------------- /mmvts/src/models/cross_encoder/bert_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/models/cross_encoder/bert_model.py -------------------------------------------------------------------------------- /mmvts/src/models/cross_encoder/ca_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/models/cross_encoder/ca_encoder.py -------------------------------------------------------------------------------- /mmvts/src/models/cross_encoder/ca_moe_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/models/cross_encoder/ca_moe_encoder.py -------------------------------------------------------------------------------- /mmvts/src/models/cross_encoder/get_cross_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/models/cross_encoder/get_cross_encoder.py -------------------------------------------------------------------------------- /mmvts/src/models/cross_encoder/ma_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/models/cross_encoder/ma_encoder.py -------------------------------------------------------------------------------- /mmvts/src/models/cross_encoder/ma_moe_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/models/cross_encoder/ma_moe_encoder.py -------------------------------------------------------------------------------- /mmvts/src/models/cross_encoder/moe.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/models/cross_encoder/moe.py -------------------------------------------------------------------------------- /mmvts/src/models/modules/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mmvts/src/models/modules/contrastive_learning_layer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/models/modules/contrastive_learning_layer.py -------------------------------------------------------------------------------- /mmvts/src/models/modules/gated_fusion.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/models/modules/gated_fusion.py -------------------------------------------------------------------------------- /mmvts/src/models/modules/loss_layer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/models/modules/loss_layer.py -------------------------------------------------------------------------------- /mmvts/src/models/multi_modal_for_ts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/models/multi_modal_for_ts.py -------------------------------------------------------------------------------- /mmvts/src/models/predictor/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mmvts/src/models/predictor/base_predictor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/models/predictor/base_predictor.py -------------------------------------------------------------------------------- /mmvts/src/models/predictor/hybrid_predictor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/models/predictor/hybrid_predictor.py -------------------------------------------------------------------------------- /mmvts/src/models/predictor/linear_predictor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/models/predictor/linear_predictor.py -------------------------------------------------------------------------------- /mmvts/src/models/predictor/topic_seg_predictor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/models/predictor/topic_seg_predictor.py -------------------------------------------------------------------------------- /mmvts/src/models/predictor/transformer_predictor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/models/predictor/transformer_predictor.py -------------------------------------------------------------------------------- /mmvts/src/models/projector/get_projector.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/models/projector/get_projector.py -------------------------------------------------------------------------------- /mmvts/src/models/projector/linear_projector.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/models/projector/linear_projector.py -------------------------------------------------------------------------------- /mmvts/src/models/projector/transformer_projector.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/models/projector/transformer_projector.py -------------------------------------------------------------------------------- /mmvts/src/models/text_encoder/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mmvts/src/models/text_encoder/text_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/models/text_encoder/text_encoder.py -------------------------------------------------------------------------------- /mmvts/src/models/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/models/utils.py -------------------------------------------------------------------------------- /mmvts/src/models/vis_encoder/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mmvts/src/models/vis_encoder/clip/__init__.py: -------------------------------------------------------------------------------- 1 | from .clip import * 2 | -------------------------------------------------------------------------------- /mmvts/src/models/vis_encoder/clip/bpe_simple_vocab_16e6.txt.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/models/vis_encoder/clip/bpe_simple_vocab_16e6.txt.gz -------------------------------------------------------------------------------- /mmvts/src/models/vis_encoder/clip/clip.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/models/vis_encoder/clip/clip.py -------------------------------------------------------------------------------- /mmvts/src/models/vis_encoder/clip/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/models/vis_encoder/clip/model.py -------------------------------------------------------------------------------- /mmvts/src/models/vis_encoder/clip/simple_tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/models/vis_encoder/clip/simple_tokenizer.py -------------------------------------------------------------------------------- /mmvts/src/models/vis_encoder/vis2d_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/models/vis_encoder/vis2d_encoder.py -------------------------------------------------------------------------------- /mmvts/src/models/vis_encoder/vis3d_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/models/vis_encoder/vis3d_encoder.py -------------------------------------------------------------------------------- /mmvts/src/models/vis_encoder/vis_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/models/vis_encoder/vis_encoder.py -------------------------------------------------------------------------------- /mmvts/src/models/vis_encoder/vis_ocr_encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/models/vis_encoder/vis_ocr_encoder.py -------------------------------------------------------------------------------- /mmvts/src/pretrain.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/pretrain.py -------------------------------------------------------------------------------- /mmvts/src/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/requirements.txt -------------------------------------------------------------------------------- /mmvts/src/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/mmvts/src/utils.py -------------------------------------------------------------------------------- /sld/.gitignore: -------------------------------------------------------------------------------- 1 | .DS_Store 2 | .idea 3 | -------------------------------------------------------------------------------- /sld/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/sld/README.md -------------------------------------------------------------------------------- /sld/fairseq/examples/hubert/simple_kmeans/WavLM.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/sld/fairseq/examples/hubert/simple_kmeans/WavLM.py -------------------------------------------------------------------------------- /sld/fairseq/examples/hubert/simple_kmeans/dump_hubert_feature.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/sld/fairseq/examples/hubert/simple_kmeans/dump_hubert_feature.py -------------------------------------------------------------------------------- /sld/fairseq/examples/hubert/simple_kmeans/dump_km.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/sld/fairseq/examples/hubert/simple_kmeans/dump_km.py -------------------------------------------------------------------------------- /sld/fairseq/examples/hubert/simple_kmeans/dump_wavlm_feature.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/sld/fairseq/examples/hubert/simple_kmeans/dump_wavlm_feature.py -------------------------------------------------------------------------------- /sld/fairseq/examples/hubert/simple_kmeans/feature_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/sld/fairseq/examples/hubert/simple_kmeans/feature_utils.py -------------------------------------------------------------------------------- /sld/fairseq/examples/hubert/simple_kmeans/learn_kmeans.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/sld/fairseq/examples/hubert/simple_kmeans/learn_kmeans.py -------------------------------------------------------------------------------- /sld/fairseq/examples/hubert/simple_kmeans/modules.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/sld/fairseq/examples/hubert/simple_kmeans/modules.py -------------------------------------------------------------------------------- /sld/fairseq/examples/wav2vec/libri_labels.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/sld/fairseq/examples/wav2vec/libri_labels.py -------------------------------------------------------------------------------- /sld/fairseq/examples/wav2vec/wav2vec_manifest.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/sld/fairseq/examples/wav2vec/wav2vec_manifest.py -------------------------------------------------------------------------------- /sld/figure/sld.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/sld/figure/sld.png -------------------------------------------------------------------------------- /sld/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/sld/requirements.txt -------------------------------------------------------------------------------- /sld/run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/sld/run.sh -------------------------------------------------------------------------------- /sld/transformers/examples/pytorch/language-modeling/run_clm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/sld/transformers/examples/pytorch/language-modeling/run_clm.py -------------------------------------------------------------------------------- /sld/utils/cer/cer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/sld/utils/cer/cer.py -------------------------------------------------------------------------------- /sld/utils/line_to_json.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/sld/utils/line_to_json.py -------------------------------------------------------------------------------- /sld/utils/run_sentencepiece.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/sld/utils/run_sentencepiece.py -------------------------------------------------------------------------------- /sld/utils/wer/wer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/sld/utils/wer/wer.py -------------------------------------------------------------------------------- /swab/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/swab/README.md -------------------------------------------------------------------------------- /swab/example/swab_example.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alibaba-damo-academy/SpokenNLP/HEAD/swab/example/swab_example.json --------------------------------------------------------------------------------