{"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/debiasing-pre-trained-contextualised","title":"Debiasing Pre-trained Contextualised Embeddings","arxiv_id":"2101.09523","date":"2021-01-23","proceeding":"EACL 2021 2","authors":["Masahiro Kaneko","Danushka Bollegala"],"abstract":"In comparison to the numerous debiasing methods proposed for the static non-contextualised word embeddings, the discriminative biases in contextualised embeddings have received relatively little attention. We propose a fine-tuning method that can be applied at token- or sentence-levels to debias pre-trained contextualised embeddings. Our proposed method can be applied to any pre-trained contextualised embedding model, without requiring to retrain those models. Using gender bias as an illustrative example, we then conduct a systematic study using several state-of-the-art (SoTA) contextualised representations on multiple benchmark datasets to evaluate the level of biases encoded in different contextualised embeddings before and after debiasing using the proposed method. We find that applying token-level debiasing for all tokens and across all layers of a contextualised embedding model produces the best performance. Interestingly, we observe that there is a trade-off between creating an accurate vs. unbiased contextualised embedding model, and different contextualised embedding models respond differently to this trade-off.","url_abs":"https://arxiv.org/abs/2101.09523v1","url_pdf":"https://arxiv.org/pdf/2101.09523v1.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":"debiasing-pre-trained-contextualised","repo_url":"https://github.com/kanekomasahiro/context-debias","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"debiasing-pre-trained-contextualised","repo_url":"https://github.com/EmpathYang/ADEPT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2101.09523","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.09523"}},"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/EmpathYang/ADEPT","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kanekomasahiro/context-debias","reach":null}],"summary":{"ran_draft_wrong":2,"ran_honours":1,"ran_fixture":1,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"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":0,"samples":[{"code_sha256_prefix":"5f516b6aaad9acb6","entry":"create_dataset","repo":"kanekomasahiro/context-debias","repo_kind":"official","path":"src/run_debias_mlm.py","file_url":"https://github.com/kanekomasahiro/context-debias/blob/HEAD/src/run_debias_mlm.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5f516b6aaad9acb6"}},{"code_sha256_prefix":"c6a0767523fa9784","entry":"encode_to_is","repo":"kanekomasahiro/context-debias","repo_kind":"official","path":"src/preprocess.py","file_url":"https://github.com/kanekomasahiro/context-debias/blob/HEAD/src/preprocess.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c6a0767523fa9784"}},{"code_sha256_prefix":"eb0a5e0c60986aa4","entry":"split_data","repo":"kanekomasahiro/context-debias","repo_kind":"official","path":"src/preprocess.py","file_url":"https://github.com/kanekomasahiro/context-debias/blob/HEAD/src/preprocess.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eb0a5e0c60986aa4"}},{"code_sha256_prefix":"d0dd7e697cd0cfba","entry":"split_data","repo":"kanekomasahiro/context-debias","repo_kind":"official","path":"src/run_debias_mlm.py","file_url":"https://github.com/kanekomasahiro/context-debias/blob/HEAD/src/run_debias_mlm.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d0dd7e697cd0cfba"}},{"code_sha256_prefix":"f123fea9fa47a462","entry":"prepare_transformer","repo":"kanekomasahiro/context-debias","repo_kind":"official","path":"src/preprocess.py","file_url":"https://github.com/kanekomasahiro/context-debias/blob/HEAD/src/preprocess.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f123fea9fa47a462"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}