{"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/an-analysis-of-simple-data-augmentation-for","title":"An Analysis of Simple Data Augmentation for Named Entity Recognition","arxiv_id":"2010.11683","date":"2020-10-22","proceeding":"COLING 2020 8","authors":["Xiang Dai","Heike Adel"],"abstract":"Simple yet effective data augmentation techniques have been proposed for sentence-level and sentence-pair natural language processing tasks. Inspired by these efforts, we design and compare data augmentation for named entity recognition, which is usually modeled as a token-level sequence labeling problem. Through experiments on two data sets from the biomedical and materials science domains (i2b2-2010 and MaSciP), we show that simple augmentation can boost performance for both recurrent and transformer-based models, especially for small training sets.","url_abs":"https://arxiv.org/abs/2010.11683v1","url_pdf":"https://arxiv.org/pdf/2010.11683v1.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":"an-analysis-of-simple-data-augmentation-for","repo_url":"https://github.com/ariepratama/syntax-driven-da","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"an-analysis-of-simple-data-augmentation-for","repo_url":"https://github.com/boschresearch/data-augmentation-coling2020","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"an-analysis-of-simple-data-augmentation-for","repo_url":"https://github.com/kajyuuen/daaja","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":"named-entity-recognition-1","task_name":"Named Entity Recognition"},{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"named-entity-recognition","task_name":"named-entity-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.11683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.11683"}},"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/boschresearch/data-augmentation-coling2020","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ariepratama/syntax-driven-da","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kajyuuen/daaja","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1,"unverified":7},"by_repo_kind":{"listed":{"samples":8,"ran":1,"repositories":2}},"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":"368a877106831d2d","entry":"get_category2mentions","repo":"boschresearch/data-augmentation-coling2020","repo_kind":"listed","path":"augment.py","file_url":"https://github.com/boschresearch/data-augmentation-coling2020/blob/HEAD/augment.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"368a877106831d2d"}},{"code_sha256_prefix":"4c4212144e799a54","entry":"get_mask_from_lengths","repo":"ariepratama/syntax-driven-da","repo_kind":"listed","path":"models.py","file_url":"https://github.com/ariepratama/syntax-driven-da/blob/HEAD/models.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4c4212144e799a54"}},{"code_sha256_prefix":"bb61bd21320504a8","entry":"get_model","repo":"ariepratama/syntax-driven-da","repo_kind":"listed","path":"augment_bert.py","file_url":"https://github.com/ariepratama/syntax-driven-da/blob/HEAD/augment_bert.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bb61bd21320504a8"}},{"code_sha256_prefix":"4af501e52576ec9c","entry":"get_spans","repo":"ariepratama/syntax-driven-da","repo_kind":"listed","path":"data.py","file_url":"https://github.com/ariepratama/syntax-driven-da/blob/HEAD/data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4af501e52576ec9c"}},{"code_sha256_prefix":"c9f2a0ba4146fe07","entry":"get_tokenizer","repo":"ariepratama/syntax-driven-da","repo_kind":"listed","path":"augment_bert.py","file_url":"https://github.com/ariepratama/syntax-driven-da/blob/HEAD/augment_bert.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c9f2a0ba4146fe07"}},{"code_sha256_prefix":"657c8bdc6ca97587","entry":"load_from_local","repo":"ariepratama/syntax-driven-da","repo_kind":"listed","path":"file_utils.py","file_url":"https://github.com/ariepratama/syntax-driven-da/blob/HEAD/file_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"657c8bdc6ca97587"}},{"code_sha256_prefix":"dba44a130bfe353b","entry":"pad_tensors","repo":"ariepratama/syntax-driven-da","repo_kind":"listed","path":"models.py","file_url":"https://github.com/ariepratama/syntax-driven-da/blob/HEAD/models.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dba44a130bfe353b"}},{"code_sha256_prefix":"1512192218dac93c","entry":"viterbi_decode","repo":"ariepratama/syntax-driven-da","repo_kind":"listed","path":"models.py","file_url":"https://github.com/ariepratama/syntax-driven-da/blob/HEAD/models.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1512192218dac93c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}