{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/revisiting-pre-trained-models-for-chinese","title":"Revisiting Pre-Trained Models for Chinese Natural Language Processing","arxiv_id":"2004.13922","date":"2020-04-29","proceeding":"Findings of the Association for Computational Linguistics 2020","authors":["Yiming Cui","Wanxiang Che","Ting Liu","Bing Qin","Shijin Wang","Guoping Hu"],"abstract":"Bidirectional Encoder Representations from Transformers (BERT) has shown marvelous improvements across various NLP tasks, and consecutive variants have been proposed to further improve the performance of the pre-trained language models. In this paper, we target on revisiting Chinese pre-trained language models to examine their effectiveness in a non-English language and release the Chinese pre-trained language model series to the community. We also propose a simple but effective model called MacBERT, which improves upon RoBERTa in several ways, especially the masking strategy that adopts MLM as correction (Mac). We carried out extensive experiments on eight Chinese NLP tasks to revisit the existing pre-trained language models as well as the proposed MacBERT. Experimental results show that MacBERT could achieve state-of-the-art performances on many NLP tasks, and we also ablate details with several findings that may help future research. Resources available: https://github.com/ymcui/MacBERT","url_abs":"https://arxiv.org/abs/2004.13922v2","url_pdf":"https://arxiv.org/pdf/2004.13922v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"revisiting-pre-trained-models-for-chinese","repo_url":"https://github.com/ymcui/MacBERT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"revisiting-pre-trained-models-for-chinese","repo_url":"https://github.com/shibing624/pycorrector","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"revisiting-pre-trained-models-for-chinese","repo_url":"https://github.com/ymcui/Chinese-BERT-wwm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"revisiting-pre-trained-models-for-chinese","repo_url":"https://github.com/ymcui/Chinese-ELECTRA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"revisiting-pre-trained-models-for-chinese","repo_url":"https://github.com/ymcui/Chinese-PreTrained-XLNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"revisiting-pre-trained-models-for-chinese","repo_url":"https://github.com/ymcui/Chinese-XLNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"stock-market-prediction","task_name":"Stock Market Prediction"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"macbert","method_name":"MacBERT"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"roberta","method_name":"RoBERTa"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[{"slug":"macbert","name":"MacBERT","full_name":"MacBERT"}],"results":[{"leaderboard":"/sota/stock-market-prediction-on-astock","task":"Stock Market Prediction","dataset":"Astock","model":"XLNET Chinese","rank_in_archive_order":13,"of":17,"metrics":{"Accuray":"61.14","F1-score":"61.19","Precision":"61.60","Recall":"61.09"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2004.13922","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.13922"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ymcui/Chinese-PreTrained-XLNet","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shibing624/pycorrector","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/ymcui/MacBERT","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/gaussic/text-classification-cnn-rnn","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ymcui/Chinese-ELECTRA","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ymcui/Chinese-BERT-wwm","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ymcui/Chinese-XLNet","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":1,"ran_honours":3,"ran_draft_wrong":4,"ran_fixture":1,"unverified":26},"by_repo_kind":{"listed":{"samples":35,"ran":9,"repositories":3}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"49538ded4b211b0d","entry":"FocalLoss","repo":"shibing624/pycorrector","repo_kind":"listed","path":"pycorrector/macbert/macbert4csc.py","file_url":"https://github.com/shibing624/pycorrector/blob/HEAD/pycorrector/macbert/macbert4csc.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"49538ded4b211b0d"}},{"code_sha256_prefix":"bc8cd524a10a5326","entry":"compute_corrector_prf","repo":"shibing624/pycorrector","repo_kind":"listed","path":"pycorrector/macbert/macbert4csc.py","file_url":"https://github.com/shibing624/pycorrector/blob/HEAD/pycorrector/macbert/macbert4csc.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bc8cd524a10a5326"}},{"code_sha256_prefix":"731b5640fb2a2a52","entry":"compute_sentence_level_prf","repo":"shibing624/pycorrector","repo_kind":"listed","path":"pycorrector/macbert/macbert4csc.py","file_url":"https://github.com/shibing624/pycorrector/blob/HEAD/pycorrector/macbert/macbert4csc.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"731b5640fb2a2a52"}},{"code_sha256_prefix":"d08f324f950148de","entry":"gelu","repo":"ymcui/Chinese-PreTrained-XLNet","repo_kind":"listed","path":"src/modeling.py","file_url":"https://github.com/ymcui/Chinese-PreTrained-XLNet/blob/HEAD/src/modeling.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d08f324f950148de"}},{"code_sha256_prefix":"aa6bc32d9c17a2f1","entry":"get_tokens","repo":"ymcui/Chinese-PreTrained-XLNet","repo_kind":"listed","path":"src/squad_utils.py","file_url":"https://github.com/ymcui/Chinese-PreTrained-XLNet/blob/HEAD/src/squad_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"aa6bc32d9c17a2f1"}},{"code_sha256_prefix":"3c707eafb83ce730","entry":"make_optimizer","repo":"shibing624/pycorrector","repo_kind":"listed","path":"pycorrector/macbert/macbert4csc.py","file_url":"https://github.com/shibing624/pycorrector/blob/HEAD/pycorrector/macbert/macbert4csc.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3c707eafb83ce730"}},{"code_sha256_prefix":"e91c44f5680827e2","entry":"make_qid_to_has_ans","repo":"ymcui/Chinese-PreTrained-XLNet","repo_kind":"listed","path":"src/squad_utils.py","file_url":"https://github.com/ymcui/Chinese-PreTrained-XLNet/blob/HEAD/src/squad_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e91c44f5680827e2"}},{"code_sha256_prefix":"6a96435eba311b08","entry":"normalize_answer","repo":"ymcui/Chinese-PreTrained-XLNet","repo_kind":"listed","path":"src/squad_utils.py","file_url":"https://github.com/ymcui/Chinese-PreTrained-XLNet/blob/HEAD/src/squad_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6a96435eba311b08"}},{"code_sha256_prefix":"9bf0f6e6298f3fbe","entry":"positional_embedding","repo":"ymcui/Chinese-PreTrained-XLNet","repo_kind":"listed","path":"src/modeling.py","file_url":"https://github.com/ymcui/Chinese-PreTrained-XLNet/blob/HEAD/src/modeling.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9bf0f6e6298f3fbe"}},{"code_sha256_prefix":"cfac541eefda5168","entry":"BaseTrainingEngine","repo":"shibing624/pycorrector","repo_kind":"listed","path":"pycorrector/macbert/macbert4csc.py","file_url":"https://github.com/shibing624/pycorrector/blob/HEAD/pycorrector/macbert/macbert4csc.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cfac541eefda5168"}},{"code_sha256_prefix":"af8425a9c3022046","entry":"CscTrainingModel","repo":"shibing624/pycorrector","repo_kind":"listed","path":"pycorrector/macbert/macbert4csc.py","file_url":"https://github.com/shibing624/pycorrector/blob/HEAD/pycorrector/macbert/macbert4csc.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"af8425a9c3022046"}},{"code_sha256_prefix":"f5ffeb1faccdd442","entry":"MacBert4Csc","repo":"shibing624/pycorrector","repo_kind":"listed","path":"pycorrector/macbert/macbert4csc.py","file_url":"https://github.com/shibing624/pycorrector/blob/HEAD/pycorrector/macbert/macbert4csc.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f5ffeb1faccdd442"}},{"code_sha256_prefix":"6b2a8f1c93d0b071","entry":"assign_to_gpu","repo":"ymcui/Chinese-PreTrained-XLNet","repo_kind":"listed","path":"src/gpu_utils.py","file_url":"https://github.com/ymcui/Chinese-PreTrained-XLNet/blob/HEAD/src/gpu_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6b2a8f1c93d0b071"}},{"code_sha256_prefix":"0e3f1e158da4c3b8","entry":"average_grads_and_vars","repo":"ymcui/Chinese-PreTrained-XLNet","repo_kind":"listed","path":"src/gpu_utils.py","file_url":"https://github.com/ymcui/Chinese-PreTrained-XLNet/blob/HEAD/src/gpu_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0e3f1e158da4c3b8"}},{"code_sha256_prefix":"8fa4efe75d3345a4","entry":"batchify","repo":"ymcui/Chinese-PreTrained-XLNet","repo_kind":"listed","path":"src/data_utils.py","file_url":"https://github.com/ymcui/Chinese-PreTrained-XLNet/blob/HEAD/src/data_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8fa4efe75d3345a4"}},{"code_sha256_prefix":"699577a393a1a36e","entry":"build_lr_scheduler","repo":"shibing624/pycorrector","repo_kind":"listed","path":"pycorrector/macbert/macbert4csc.py","file_url":"https://github.com/shibing624/pycorrector/blob/HEAD/pycorrector/macbert/macbert4csc.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"699577a393a1a36e"}},{"code_sha256_prefix":"09d1e0e9c15a4503","entry":"configure_tpu","repo":"ymcui/Chinese-PreTrained-XLNet","repo_kind":"listed","path":"src/model_utils.py","file_url":"https://github.com/ymcui/Chinese-PreTrained-XLNet/blob/HEAD/src/model_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"09d1e0e9c15a4503"}},{"code_sha256_prefix":"c09b2ad22d30dc58","entry":"construct_scalar_host_call","repo":"ymcui/Chinese-PreTrained-XLNet","repo_kind":"listed","path":"src/function_builder.py","file_url":"https://github.com/ymcui/Chinese-PreTrained-XLNet/blob/HEAD/src/function_builder.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c09b2ad22d30dc58"}},{"code_sha256_prefix":"b03d45af664a39e3","entry":"create_int_feature","repo":"ymcui/Chinese-ELECTRA","repo_kind":"listed","path":"build_pretraining_dataset.py","file_url":"https://github.com/ymcui/Chinese-ELECTRA/blob/HEAD/build_pretraining_dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b03d45af664a39e3"}},{"code_sha256_prefix":"b9e225229ba459c3","entry":"create_run_config","repo":"ymcui/Chinese-PreTrained-XLNet","repo_kind":"listed","path":"src/xlnet.py","file_url":"https://github.com/ymcui/Chinese-PreTrained-XLNet/blob/HEAD/src/xlnet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b9e225229ba459c3"}},{"code_sha256_prefix":"8e58d7fe314fa0a1","entry":"create_tfrecords","repo":"ymcui/Chinese-PreTrained-XLNet","repo_kind":"listed","path":"src/data_utils.py","file_url":"https://github.com/ymcui/Chinese-PreTrained-XLNet/blob/HEAD/src/data_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8e58d7fe314fa0a1"}},{"code_sha256_prefix":"5abf0267f0fc7514","entry":"embedding_lookup","repo":"ymcui/Chinese-PreTrained-XLNet","repo_kind":"listed","path":"src/modeling.py","file_url":"https://github.com/ymcui/Chinese-PreTrained-XLNet/blob/HEAD/src/modeling.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5abf0267f0fc7514"}},{"code_sha256_prefix":"0de7059b7a331eb0","entry":"encode_pieces","repo":"ymcui/Chinese-PreTrained-XLNet","repo_kind":"listed","path":"src/prepro_utils.py","file_url":"https://github.com/ymcui/Chinese-PreTrained-XLNet/blob/HEAD/src/prepro_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0de7059b7a331eb0"}},{"code_sha256_prefix":"aab5156ced02aa8a","entry":"file_based_input_fn_builder","repo":"ymcui/Chinese-PreTrained-XLNet","repo_kind":"listed","path":"src/run_classifier.py","file_url":"https://github.com/ymcui/Chinese-PreTrained-XLNet/blob/HEAD/src/run_classifier.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"aab5156ced02aa8a"}},{"code_sha256_prefix":"b71224516be1ddfa","entry":"find_lcs","repo":"ymcui/Chinese-ELECTRA","repo_kind":"listed","path":"cmrc2018_drcd_evaluate.py","file_url":"https://github.com/ymcui/Chinese-ELECTRA/blob/HEAD/cmrc2018_drcd_evaluate.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b71224516be1ddfa"}},{"code_sha256_prefix":"b86bea980cfb5cbf","entry":"format_filename","repo":"ymcui/Chinese-PreTrained-XLNet","repo_kind":"listed","path":"src/data_utils.py","file_url":"https://github.com/ymcui/Chinese-PreTrained-XLNet/blob/HEAD/src/data_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b86bea980cfb5cbf"}},{"code_sha256_prefix":"9c6c6f379ebe0c8e","entry":"gelu","repo":"ymcui/Chinese-ELECTRA","repo_kind":"listed","path":"model/modeling.py","file_url":"https://github.com/ymcui/Chinese-ELECTRA/blob/HEAD/model/modeling.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9c6c6f379ebe0c8e"}},{"code_sha256_prefix":"b2dfae5f1625da67","entry":"get_activation","repo":"ymcui/Chinese-ELECTRA","repo_kind":"listed","path":"model/modeling.py","file_url":"https://github.com/ymcui/Chinese-ELECTRA/blob/HEAD/model/modeling.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b2dfae5f1625da67"}},{"code_sha256_prefix":"cb34c9c201e23b66","entry":"get_assignment_map_from_checkpoint","repo":"ymcui/Chinese-ELECTRA","repo_kind":"listed","path":"model/modeling.py","file_url":"https://github.com/ymcui/Chinese-ELECTRA/blob/HEAD/model/modeling.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cb34c9c201e23b66"}},{"code_sha256_prefix":"7b1d9794b90b3ae2","entry":"init_from_checkpoint","repo":"ymcui/Chinese-PreTrained-XLNet","repo_kind":"listed","path":"src/model_utils.py","file_url":"https://github.com/ymcui/Chinese-PreTrained-XLNet/blob/HEAD/src/model_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7b1d9794b90b3ae2"}},{"code_sha256_prefix":"3d6b054785523852","entry":"load_from_checkpoint","repo":"ymcui/Chinese-PreTrained-XLNet","repo_kind":"listed","path":"src/gpu_utils.py","file_url":"https://github.com/ymcui/Chinese-PreTrained-XLNet/blob/HEAD/src/gpu_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3d6b054785523852"}},{"code_sha256_prefix":"2ac9d5179c0b5c85","entry":"mixed_segmentation","repo":"ymcui/Chinese-ELECTRA","repo_kind":"listed","path":"cmrc2018_drcd_evaluate.py","file_url":"https://github.com/ymcui/Chinese-ELECTRA/blob/HEAD/cmrc2018_drcd_evaluate.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2ac9d5179c0b5c85"}},{"code_sha256_prefix":"b19697c998adb1ea","entry":"preprocess_text","repo":"ymcui/Chinese-PreTrained-XLNet","repo_kind":"listed","path":"src/prepro_utils.py","file_url":"https://github.com/ymcui/Chinese-PreTrained-XLNet/blob/HEAD/src/prepro_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b19697c998adb1ea"}},{"code_sha256_prefix":"0e5615f8994003cf","entry":"printable_text","repo":"ymcui/Chinese-PreTrained-XLNet","repo_kind":"listed","path":"src/prepro_utils.py","file_url":"https://github.com/ymcui/Chinese-PreTrained-XLNet/blob/HEAD/src/prepro_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0e5615f8994003cf"}},{"code_sha256_prefix":"5a2e0cd001c9f26b","entry":"remove_punctuation","repo":"ymcui/Chinese-ELECTRA","repo_kind":"listed","path":"cmrc2018_drcd_evaluate.py","file_url":"https://github.com/ymcui/Chinese-ELECTRA/blob/HEAD/cmrc2018_drcd_evaluate.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5a2e0cd001c9f26b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}