{"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/softeda-rethinking-rule-based-data","title":"SoftEDA: Rethinking Rule-Based Data Augmentation with Soft Labels","arxiv_id":"2402.05591","date":"2024-02-08","proceeding":null,"authors":["Juhwan Choi","Kyohoon Jin","Junho Lee","Sangmin Song","Youngbin Kim"],"abstract":"Rule-based text data augmentation is widely used for NLP tasks due to its simplicity. However, this method can potentially damage the original meaning of the text, ultimately hurting the performance of the model. To overcome this limitation, we propose a straightforward technique for applying soft labels to augmented data. We conducted experiments across seven different classification tasks and empirically demonstrated the effectiveness of our proposed approach. We have publicly opened our source code for reproducibility.","url_abs":"https://arxiv.org/abs/2402.05591v1","url_pdf":"https://arxiv.org/pdf/2402.05591v1.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":"softeda-rethinking-rule-based-data","repo_url":"https://github.com/c-juhwan/softeda","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.05591","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05591"}},"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/c-juhwan/softeda","reach":null}],"summary":{"ran_draft_wrong":6,"unverified":7},"by_repo_kind":{"official":{"samples":13,"ran":6,"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":13,"samples":[{"code_sha256_prefix":"7dff4d435aa3b366","entry":"aeda_random_insertion","repo":"c-juhwan/softeda","repo_kind":"official","path":"task/classification/augmentation.py","file_url":"https://github.com/c-juhwan/softeda/blob/HEAD/task/classification/augmentation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7dff4d435aa3b366"}},{"code_sha256_prefix":"848bf220f70cc1bd","entry":"get_huggingface_model_name","repo":"c-juhwan/softeda","repo_kind":"official","path":"task/classification/augmentation.py","file_url":"https://github.com/c-juhwan/softeda/blob/HEAD/task/classification/augmentation.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":"848bf220f70cc1bd"}},{"code_sha256_prefix":"665498debbd97069","entry":"random_deletion","repo":"c-juhwan/softeda","repo_kind":"official","path":"task/classification/augmentation.py","file_url":"https://github.com/c-juhwan/softeda/blob/HEAD/task/classification/augmentation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"665498debbd97069"}},{"code_sha256_prefix":"5db9c6d796298c60","entry":"random_swap","repo":"c-juhwan/softeda","repo_kind":"official","path":"task/classification/augmentation.py","file_url":"https://github.com/c-juhwan/softeda/blob/HEAD/task/classification/augmentation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5db9c6d796298c60"}},{"code_sha256_prefix":"af951d4a30b7cde2","entry":"run_aeda","repo":"c-juhwan/softeda","repo_kind":"official","path":"task/classification/augmentation.py","file_url":"https://github.com/c-juhwan/softeda/blob/HEAD/task/classification/augmentation.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":"af951d4a30b7cde2"}},{"code_sha256_prefix":"d4988e06b78e03b2","entry":"swap_word","repo":"c-juhwan/softeda","repo_kind":"official","path":"task/classification/augmentation.py","file_url":"https://github.com/c-juhwan/softeda/blob/HEAD/task/classification/augmentation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d4988e06b78e03b2"}},{"code_sha256_prefix":"24a378ab7ad67821","entry":"add_word","repo":"c-juhwan/softeda","repo_kind":"official","path":"task/classification/augmentation.py","file_url":"https://github.com/c-juhwan/softeda/blob/HEAD/task/classification/augmentation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"24a378ab7ad67821"}},{"code_sha256_prefix":"e0b8483581ba66c3","entry":"augmentation","repo":"c-juhwan/softeda","repo_kind":"official","path":"task/classification/augmentation.py","file_url":"https://github.com/c-juhwan/softeda/blob/HEAD/task/classification/augmentation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e0b8483581ba66c3"}},{"code_sha256_prefix":"eac80e3c40b7b6d9","entry":"get_synonyms","repo":"c-juhwan/softeda","repo_kind":"official","path":"task/classification/augmentation.py","file_url":"https://github.com/c-juhwan/softeda/blob/HEAD/task/classification/augmentation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eac80e3c40b7b6d9"}},{"code_sha256_prefix":"9d9e39f0d37cff1b","entry":"load_preprocessed_data","repo":"c-juhwan/softeda","repo_kind":"official","path":"task/classification/augmentation.py","file_url":"https://github.com/c-juhwan/softeda/blob/HEAD/task/classification/augmentation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9d9e39f0d37cff1b"}},{"code_sha256_prefix":"923a349e97b3a33a","entry":"random_insertion","repo":"c-juhwan/softeda","repo_kind":"official","path":"task/classification/augmentation.py","file_url":"https://github.com/c-juhwan/softeda/blob/HEAD/task/classification/augmentation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"923a349e97b3a33a"}},{"code_sha256_prefix":"43eaf44f643ba4d6","entry":"run_eda","repo":"c-juhwan/softeda","repo_kind":"official","path":"task/classification/augmentation.py","file_url":"https://github.com/c-juhwan/softeda/blob/HEAD/task/classification/augmentation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"43eaf44f643ba4d6"}},{"code_sha256_prefix":"8526ff14983c5278","entry":"synonym_replacement","repo":"c-juhwan/softeda","repo_kind":"official","path":"task/classification/augmentation.py","file_url":"https://github.com/c-juhwan/softeda/blob/HEAD/task/classification/augmentation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8526ff14983c5278"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}