{"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/conditional-bert-contextual-augmentation","title":"Conditional BERT Contextual Augmentation","arxiv_id":"1812.06705","date":"2018-12-17","proceeding":null,"authors":["Xing Wu","Shangwen Lv","Liangjun Zang","Jizhong Han","Songlin Hu"],"abstract":"We propose a novel data augmentation method for labeled sentences called\nconditional BERT contextual augmentation. Data augmentation methods are often\napplied to prevent overfitting and improve generalization of deep neural\nnetwork models. Recently proposed contextual augmentation augments labeled\nsentences by randomly replacing words with more varied substitutions predicted\nby language model. BERT demonstrates that a deep bidirectional language model\nis more powerful than either an unidirectional language model or the shallow\nconcatenation of a forward and backward model. We retrofit BERT to conditional\nBERT by introducing a new conditional masked language model\\footnote{The term\n\"conditional masked language model\" appeared once in original BERT paper, which\nindicates context-conditional, is equivalent to term \"masked language model\".\nIn our paper, \"conditional masked language model\" indicates we apply extra\nlabel-conditional constraint to the \"masked language model\".} task. The well\ntrained conditional BERT can be applied to enhance contextual augmentation.\nExperiments on six various different text classification tasks show that our\nmethod can be easily applied to both convolutional or recurrent neural networks\nclassifier to obtain obvious improvement.","url_abs":"http://arxiv.org/abs/1812.06705v1","url_pdf":"http://arxiv.org/pdf/1812.06705v1.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":"conditional-bert-contextual-augmentation","repo_url":"https://github.com/1024er/cbert_aug","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"conditional-bert-contextual-augmentation","repo_url":"https://github.com/IIEKES/cbert_aug","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"conditional-bert-contextual-augmentation","repo_url":"https://github.com/IIEKES/cbert_aug_deprecated","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"conditional-bert-contextual-augmentation","repo_url":"https://github.com/newRevelation/DL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"conditional-bert-contextual-augmentation","repo_url":"https://github.com/woailaosang/repo_treasure","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"text-classification","task_name":"Text Classification"}],"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":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1812.06705","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.06705"}},"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/newRevelation/DL","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/IIEKES/cbert_aug_deprecated","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/IIEKES/cbert_aug","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/woailaosang/repo_treasure","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/1024er/cbert_aug","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{"listed":{"samples":2,"ran":2,"repositories":1}},"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":2,"samples":[{"code_sha256_prefix":"fbd849b3c76a8666","entry":"convert_examples_to_features","repo":"newRevelation/DL","repo_kind":"listed","path":"aug_dataset.py","file_url":"https://github.com/newRevelation/DL/blob/HEAD/aug_dataset.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fbd849b3c76a8666"}},{"code_sha256_prefix":"cece32072ae775e8","entry":"rev_wordpiece","repo":"newRevelation/DL","repo_kind":"listed","path":"aug_dataset.py","file_url":"https://github.com/newRevelation/DL/blob/HEAD/aug_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cece32072ae775e8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}