{"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/data-augmentation-using-pre-trained","title":"Data Augmentation using Pre-trained Transformer Models","arxiv_id":"2003.02245","date":"2020-03-04","proceeding":"AACL (lifelongnlp) 2020 12","authors":["Varun Kumar","Ashutosh Choudhary","Eunah Cho"],"abstract":"Language model based pre-trained models such as BERT have provided significant gains across different NLP tasks. In this paper, we study different types of transformer based pre-trained models such as auto-regressive models (GPT-2), auto-encoder models (BERT), and seq2seq models (BART) for conditional data augmentation. We show that prepending the class labels to text sequences provides a simple yet effective way to condition the pre-trained models for data augmentation. Additionally, on three classification benchmarks, pre-trained Seq2Seq model outperforms other data augmentation methods in a low-resource setting. Further, we explore how different pre-trained model based data augmentation differs in-terms of data diversity, and how well such methods preserve the class-label information.","url_abs":"https://arxiv.org/abs/2003.02245v2","url_pdf":"https://arxiv.org/pdf/2003.02245v2.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":"data-augmentation-using-pre-trained","repo_url":"https://github.com/varinf/TransformersDataAugmentation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"data-augmentation-using-pre-trained","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":"data-augmentation-using-pre-trained","repo_url":"https://github.com/megagonlabs/rotom","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"data-augmentation-using-pre-trained","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":"diversity","task_name":"Diversity"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"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":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"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":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"seq2seq","method_name":"Seq2Seq"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"},{"method_slug":"transformer","method_name":"Transformer"},{"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=2003.02245","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.02245"}},"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/varinf/TransformersDataAugmentation","reach":{"status":"ok","spdx":"NOASSERTION"}},{"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/kajyuuen/daaja","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/megagonlabs/rotom","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"summary":{"unverified":9},"by_repo_kind":{"listed":{"samples":9,"ran":0,"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":0,"samples":[{"code_sha256_prefix":"10336645e650e18c","entry":"auto_mixda","repo":"megagonlabs/rotom","repo_kind":"listed","path":"rotom/auto_mixda.py","file_url":"https://github.com/megagonlabs/rotom/blob/HEAD/rotom/auto_mixda.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"10336645e650e18c"}},{"code_sha256_prefix":"b75fcb376dd932d9","entry":"evaluate","repo":"megagonlabs/rotom","repo_kind":"listed","path":"ditto/dm.py","file_url":"https://github.com/megagonlabs/rotom/blob/HEAD/ditto/dm.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"b75fcb376dd932d9"}},{"code_sha256_prefix":"d5838e93b4af1c05","entry":"generate","repo":"megagonlabs/rotom","repo_kind":"listed","path":"invda/generate.py","file_url":"https://github.com/megagonlabs/rotom/blob/HEAD/invda/generate.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"d5838e93b4af1c05"}},{"code_sha256_prefix":"dfa300b83dc454b7","entry":"get_lm","repo":"megagonlabs/rotom","repo_kind":"listed","path":"rotom/model.py","file_url":"https://github.com/megagonlabs/rotom/blob/HEAD/rotom/model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"dfa300b83dc454b7"}},{"code_sha256_prefix":"4865d9d12d7048ee","entry":"get_ops","repo":"megagonlabs/rotom","repo_kind":"listed","path":"train_any.py","file_url":"https://github.com/megagonlabs/rotom/blob/HEAD/train_any.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"4865d9d12d7048ee"}},{"code_sha256_prefix":"44e9efdba5cd8f3c","entry":"process_filter","repo":"megagonlabs/rotom","repo_kind":"listed","path":"rotom/auto_filter_weight.py","file_url":"https://github.com/megagonlabs/rotom/blob/HEAD/rotom/auto_filter_weight.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"44e9efdba5cd8f3c"}},{"code_sha256_prefix":"05741498b43e4e31","entry":"sharpen","repo":"megagonlabs/rotom","repo_kind":"listed","path":"rotom/auto_filter_weight.py","file_url":"https://github.com/megagonlabs/rotom/blob/HEAD/rotom/auto_filter_weight.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"05741498b43e4e31"}},{"code_sha256_prefix":"b82757d05d446661","entry":"sharpen","repo":"megagonlabs/rotom","repo_kind":"listed","path":"rotom/auto_mixda.py","file_url":"https://github.com/megagonlabs/rotom/blob/HEAD/rotom/auto_mixda.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"b82757d05d446661"}},{"code_sha256_prefix":"d7b285f99ad179f7","entry":"sharpen_onehot","repo":"megagonlabs/rotom","repo_kind":"listed","path":"rotom/auto_filter_weight.py","file_url":"https://github.com/megagonlabs/rotom/blob/HEAD/rotom/auto_filter_weight.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"d7b285f99ad179f7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}