{"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/text-detoxification-using-large-pre-trained","title":"Text Detoxification using Large Pre-trained Neural Models","arxiv_id":"2109.08914","date":"2021-09-18","proceeding":"EMNLP 2021 11","authors":["David Dale","Anton Voronov","Daryna Dementieva","Varvara Logacheva","Olga Kozlova","Nikita Semenov","Alexander Panchenko"],"abstract":"We present two novel unsupervised methods for eliminating toxicity in text. Our first method combines two recent ideas: (1) guidance of the generation process with small style-conditional language models and (2) use of paraphrasing models to perform style transfer. We use a well-performing paraphraser guided by style-trained language models to keep the text content and remove toxicity. Our second method uses BERT to replace toxic words with their non-offensive synonyms. We make the method more flexible by enabling BERT to replace mask tokens with a variable number of words. Finally, we present the first large-scale comparative study of style transfer models on the task of toxicity removal. We compare our models with a number of methods for style transfer. The models are evaluated in a reference-free way using a combination of unsupervised style transfer metrics. Both methods we suggest yield new SOTA results.","url_abs":"https://arxiv.org/abs/2109.08914v2","url_pdf":"https://arxiv.org/pdf/2109.08914v2.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":"text-detoxification-using-large-pre-trained","repo_url":"https://github.com/skoltech-nlp/detox","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"style-transfer","task_name":"Style Transfer"}],"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=2109.08914","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.08914"}},"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/skoltech-nlp/detox","reach":null}],"summary":{"ran":1,"ran_draft_wrong":2,"ran_honours":1},"by_repo_kind":{"official":{"samples":4,"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":4,"samples":[{"code_sha256_prefix":"e47093acc32353c3","entry":"CondBertRewriter","repo":"skoltech-nlp/detox","repo_kind":"official","path":"emnlp2021/style_transfer/condBERT/condbert.py","file_url":"https://github.com/skoltech-nlp/detox/blob/HEAD/emnlp2021/style_transfer/condBERT/condbert.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e47093acc32353c3"}},{"code_sha256_prefix":"da47f8d108073a00","entry":"default_chooser","repo":"skoltech-nlp/detox","repo_kind":"official","path":"emnlp2021/style_transfer/condBERT/condbert.py","file_url":"https://github.com/skoltech-nlp/detox/blob/HEAD/emnlp2021/style_transfer/condBERT/condbert.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"da47f8d108073a00"}},{"code_sha256_prefix":"8fe2837914153e91","entry":"get_ll","repo":"skoltech-nlp/detox","repo_kind":"official","path":"emnlp2021/style_transfer/condBERT/condbert.py","file_url":"https://github.com/skoltech-nlp/detox/blob/HEAD/emnlp2021/style_transfer/condBERT/condbert.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8fe2837914153e91"}},{"code_sha256_prefix":"0617b9bc6327cd77","entry":"group_by_first_token","repo":"skoltech-nlp/detox","repo_kind":"official","path":"emnlp2021/style_transfer/condBERT/condbert.py","file_url":"https://github.com/skoltech-nlp/detox/blob/HEAD/emnlp2021/style_transfer/condBERT/condbert.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":"0617b9bc6327cd77"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}