{"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/eda-easy-data-augmentation-techniques-for","title":"EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks","arxiv_id":"1901.11196","date":"2019-01-31","proceeding":"IJCNLP 2019 11","authors":["Jason Wei","Kai Zou"],"abstract":"We present EDA: easy data augmentation techniques for boosting performance on text classification tasks. EDA consists of four simple but powerful operations: synonym replacement, random insertion, random swap, and random deletion. On five text classification tasks, we show that EDA improves performance for both convolutional and recurrent neural networks. EDA demonstrates particularly strong results for smaller datasets; on average, across five datasets, training with EDA while using only 50% of the available training set achieved the same accuracy as normal training with all available data. We also performed extensive ablation studies and suggest parameters for practical use.","url_abs":"https://arxiv.org/abs/1901.11196v2","url_pdf":"https://arxiv.org/pdf/1901.11196v2.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":"eda-easy-data-augmentation-techniques-for","repo_url":"https://github.com/jasonwei20/eda_nlp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"eda-easy-data-augmentation-techniques-for","repo_url":"https://github.com/BPYap/Question-Generation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"eda-easy-data-augmentation-techniques-for","repo_url":"https://github.com/WengLab-InformaticsResearch/UMLS-EDA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"eda-easy-data-augmentation-techniques-for","repo_url":"https://github.com/aflah02/Easy-Data-Augmentation-Implementation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"eda-easy-data-augmentation-techniques-for","repo_url":"https://github.com/akkarimi/aeda_nlp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"eda-easy-data-augmentation-techniques-for","repo_url":"https://github.com/alikhodadoost/Persian-Sentence-Augmenter","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"eda-easy-data-augmentation-techniques-for","repo_url":"https://github.com/hshrimp/EDA4Chinese","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"eda-easy-data-augmentation-techniques-for","repo_url":"https://github.com/hshrimp/EDA_BackTranslate_For_Chinese","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"eda-easy-data-augmentation-techniques-for","repo_url":"https://github.com/jaaack-wang/linguistic-knowledge-in-DA-for-NLP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"paddle","reach":{"status":"ok"}},{"paper_slug":"eda-easy-data-augmentation-techniques-for","repo_url":"https://github.com/kajyuuen/daaja","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"eda-easy-data-augmentation-techniques-for","repo_url":"https://github.com/lbneon/research","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"eda-easy-data-augmentation-techniques-for","repo_url":"https://github.com/lmcango/YCNG-229","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"eda-easy-data-augmentation-techniques-for","repo_url":"https://github.com/oraby8/TextDataAug","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"eda-easy-data-augmentation-techniques-for","repo_url":"https://github.com/wac81/textda","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"eda-easy-data-augmentation-techniques-for","repo_url":"https://github.com/dsfsi/textaugment","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"eda-easy-data-augmentation-techniques-for","repo_url":"https://github.com/makcedward/nlpaug","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"subjectivity-analysis","task_name":"Subjectivity Analysis"},{"task_slug":"text-augmentation","task_name":"Text Augmentation"},{"task_slug":"text-classification","task_name":"Text Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1901.11196","atlas_url":"https://app.syntology.ai/?focus=1901.11196","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.11196"}},"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/aflah02/Easy-Data-Augmentation-Implementation","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wac81/textda","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/WengLab-InformaticsResearch/UMLS-EDA","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/oraby8/TextDataAug","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alikhodadoost/Persian-Sentence-Augmenter","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/makcedward/nlpaug","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lbneon/research","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/akkarimi/aeda_nlp","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hshrimp/EDA4Chinese","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kajyuuen/daaja","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dsfsi/textaugment","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jaaack-wang/linguistic-knowledge-in-DA-for-NLP","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hshrimp/EDA_BackTranslate_For_Chinese","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jasonwei20/eda_nlp","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/BPYap/Question-Generation","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lmcango/YCNG-229","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":2,"ran":7,"unverified":4},"by_repo_kind":{"listed":{"samples":13,"ran":9,"repositories":4}},"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":1,"samples":[{"code_sha256_prefix":"f15117422b72cf43","entry":"get_only_chars","repo":"WengLab-InformaticsResearch/UMLS-EDA","repo_kind":"listed","path":"src/eda4ner.py","file_url":"https://github.com/WengLab-InformaticsResearch/UMLS-EDA/blob/HEAD/src/eda4ner.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f15117422b72cf43"}},{"code_sha256_prefix":"98189c47c8a85a19","entry":"get_reuslt","repo":"wac81/textda","repo_kind":"listed","path":"textda/youdao_translate.py","file_url":"https://github.com/wac81/textda/blob/HEAD/textda/youdao_translate.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"98189c47c8a85a19"}},{"code_sha256_prefix":"b3980810c3d6ee0e","entry":"get_umls_tagging","repo":"WengLab-InformaticsResearch/UMLS-EDA","repo_kind":"listed","path":"src/eda.py","file_url":"https://github.com/WengLab-InformaticsResearch/UMLS-EDA/blob/HEAD/src/eda.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b3980810c3d6ee0e"}},{"code_sha256_prefix":"ec7f7431d2ab05b8","entry":"insert_punctuation_marks","repo":"akkarimi/aeda_nlp","repo_kind":"listed","path":"code/aeda.py","file_url":"https://github.com/akkarimi/aeda_nlp/blob/HEAD/code/aeda.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":"ec7f7431d2ab05b8"}},{"code_sha256_prefix":"2b0a89c441da11e0","entry":"isSubstring","repo":"WengLab-InformaticsResearch/UMLS-EDA","repo_kind":"listed","path":"src/eda4ner.py","file_url":"https://github.com/WengLab-InformaticsResearch/UMLS-EDA/blob/HEAD/src/eda4ner.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2b0a89c441da11e0"}},{"code_sha256_prefix":"3f9990a17de8c7cd","entry":"is_fa","repo":"alikhodadoost/Persian-Sentence-Augmenter","repo_kind":"listed","path":"augment/utils.py","file_url":"https://github.com/alikhodadoost/Persian-Sentence-Augmenter/blob/HEAD/augment/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3f9990a17de8c7cd"}},{"code_sha256_prefix":"140cb152d5a22b11","entry":"ngram_index","repo":"WengLab-InformaticsResearch/UMLS-EDA","repo_kind":"listed","path":"src/eda4ner.py","file_url":"https://github.com/WengLab-InformaticsResearch/UMLS-EDA/blob/HEAD/src/eda4ner.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"140cb152d5a22b11"}},{"code_sha256_prefix":"98d52939796d3671","entry":"preprocess","repo":"alikhodadoost/Persian-Sentence-Augmenter","repo_kind":"listed","path":"augment/utils.py","file_url":"https://github.com/alikhodadoost/Persian-Sentence-Augmenter/blob/HEAD/augment/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"98d52939796d3671"}},{"code_sha256_prefix":"1e0ed12d526c0770","entry":"remove_puncs","repo":"alikhodadoost/Persian-Sentence-Augmenter","repo_kind":"listed","path":"augment/utils.py","file_url":"https://github.com/alikhodadoost/Persian-Sentence-Augmenter/blob/HEAD/augment/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1e0ed12d526c0770"}},{"code_sha256_prefix":"f9a184ef8baefe79","entry":"get_atoms","repo":"WengLab-InformaticsResearch/UMLS-EDA","repo_kind":"listed","path":"src/eda.py","file_url":"https://github.com/WengLab-InformaticsResearch/UMLS-EDA/blob/HEAD/src/eda.py","link_basis":"harvester_set","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":"f9a184ef8baefe79"}},{"code_sha256_prefix":"2dacb6d9d554e193","entry":"get_only_chars","repo":"WengLab-InformaticsResearch/UMLS-EDA","repo_kind":"listed","path":"src/eda.py","file_url":"https://github.com/WengLab-InformaticsResearch/UMLS-EDA/blob/HEAD/src/eda.py","link_basis":"harvester_set","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":"2dacb6d9d554e193"}},{"code_sha256_prefix":"fff3d19c06e6480c","entry":"read_text_src","repo":"wac81/textda","repo_kind":"listed","path":"textda/youdao_translate.py","file_url":"https://github.com/wac81/textda/blob/HEAD/textda/youdao_translate.py","link_basis":"harvester_set","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":"fff3d19c06e6480c"}},{"code_sha256_prefix":"be53242ffe2dc1e4","entry":"translate","repo":"wac81/textda","repo_kind":"listed","path":"textda/youdao_translate.py","file_url":"https://github.com/wac81/textda/blob/HEAD/textda/youdao_translate.py","link_basis":"harvester_set","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":"be53242ffe2dc1e4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}