{"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/towards-robustness-to-label-noise-in-text","title":"Towards Robustness to Label Noise in Text Classification via Noise Modeling","arxiv_id":"2101.11214","date":"2021-01-27","proceeding":null,"authors":["Siddhant Garg","Goutham Ramakrishnan","Varun Thumbe"],"abstract":"Large datasets in NLP suffer from noisy labels, due to erroneous automatic and human annotation procedures. We study the problem of text classification with label noise, and aim to capture this noise through an auxiliary noise model over the classifier. We first assign a probability score to each training sample of having a noisy label, through a beta mixture model fitted on the losses at an early epoch of training. Then, we use this score to selectively guide the learning of the noise model and classifier. Our empirical evaluation on two text classification tasks shows that our approach can improve over the baseline accuracy, and prevent over-fitting to the noise.","url_abs":"https://arxiv.org/abs/2101.11214v3","url_pdf":"https://arxiv.org/pdf/2101.11214v3.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":"towards-robustness-to-label-noise-in-text","repo_url":"https://github.com/thumbe3/label-noise-nlp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"learning-with-noisy-labels","task_name":"Learning with noisy labels"},{"task_slug":"multi-label-text-classification","task_name":"Multi-Label Text Classification"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2101.11214","atlas_url":"https://app.syntology.ai/?focus=2101.11214","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.11214"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/thumbe3/label-noise-nlp","reach":null}],"summary":{"ran_violates":2,"ran_draft_wrong":2},"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":"f352c136b669e21e","entry":"contain_how_what","repo":"thumbe3/label-noise-nlp","repo_kind":"official","path":"add_noise.py","file_url":"https://github.com/thumbe3/label-noise-nlp/blob/HEAD/add_noise.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f352c136b669e21e"}},{"code_sha256_prefix":"379639ccd50948f7","entry":"contain_reuter","repo":"thumbe3/label-noise-nlp","repo_kind":"official","path":"add_noise.py","file_url":"https://github.com/thumbe3/label-noise-nlp/blob/HEAD/add_noise.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"379639ccd50948f7"}},{"code_sha256_prefix":"2e0740f9258c4c0c","entry":"eval_model","repo":"thumbe3/label-noise-nlp","repo_kind":"official","path":"train_classifier.py","file_url":"https://github.com/thumbe3/label-noise-nlp/blob/HEAD/train_classifier.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2e0740f9258c4c0c"}},{"code_sha256_prefix":"958b1db10ac8c6a6","entry":"eval_model_noisy","repo":"thumbe3/label-noise-nlp","repo_kind":"official","path":"train_classifier.py","file_url":"https://github.com/thumbe3/label-noise-nlp/blob/HEAD/train_classifier.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"958b1db10ac8c6a6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}