{"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/deformer-decomposing-pre-trained-transformers","title":"DeFormer: Decomposing Pre-trained Transformers for Faster Question Answering","arxiv_id":"2005.00697","date":"2020-05-02","proceeding":"ACL 2020 6","authors":["Qingqing Cao","Harsh Trivedi","Aruna Balasubramanian","Niranjan Balasubramanian"],"abstract":"Transformer-based QA models use input-wide self-attention -- i.e. across both the question and the input passage -- at all layers, causing them to be slow and memory-intensive. It turns out that we can get by without input-wide self-attention at all layers, especially in the lower layers. We introduce DeFormer, a decomposed transformer, which substitutes the full self-attention with question-wide and passage-wide self-attentions in the lower layers. This allows for question-independent processing of the input text representations, which in turn enables pre-computing passage representations reducing runtime compute drastically. Furthermore, because DeFormer is largely similar to the original model, we can initialize DeFormer with the pre-training weights of a standard transformer, and directly fine-tune on the target QA dataset. We show DeFormer versions of BERT and XLNet can be used to speed up QA by over 4.3x and with simple distillation-based losses they incur only a 1% drop in accuracy. We open source the code at https://github.com/StonyBrookNLP/deformer.","url_abs":"https://arxiv.org/abs/2005.00697v1","url_pdf":"https://arxiv.org/pdf/2005.00697v1.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":"deformer-decomposing-pre-trained-transformers","repo_url":"https://github.com/StonyBrookNLP/deformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[{"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":"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":"residual-connection","method_name":"Residual Connection"},{"method_slug":"speed","method_name":"SPEED"},{"method_slug":"sentencepiece","method_name":"SentencePiece"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"},{"method_slug":"xlnet","method_name":"XLNet"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2005.00697","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.00697"}},"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/StonyBrookNLP/deformer","reach":null}],"summary":{"ran_honours":1,"ran_draft_wrong":2,"unverified":3},"by_repo_kind":{"official":{"samples":6,"ran":3,"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":"aa3f814034078dc9","entry":"gelu","repo":"StonyBrookNLP/deformer","repo_kind":"official","path":"models/layers/transformer.py","file_url":"https://github.com/StonyBrookNLP/deformer/blob/HEAD/models/layers/transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aa3f814034078dc9"}},{"code_sha256_prefix":"cda2eae6b468a58a","entry":"get_activation","repo":"StonyBrookNLP/deformer","repo_kind":"official","path":"models/layers/transformer.py","file_url":"https://github.com/StonyBrookNLP/deformer/blob/HEAD/models/layers/transformer.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cda2eae6b468a58a"}},{"code_sha256_prefix":"4f59e68b4035cf8a","entry":"get_initializer","repo":"StonyBrookNLP/deformer","repo_kind":"official","path":"models/layers/transformer.py","file_url":"https://github.com/StonyBrookNLP/deformer/blob/HEAD/models/layers/transformer.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4f59e68b4035cf8a"}},{"code_sha256_prefix":"fe2a344ff9027718","entry":"BertEncoder","repo":"StonyBrookNLP/deformer","repo_kind":"official","path":"models/layers/transformer.py","file_url":"https://github.com/StonyBrookNLP/deformer/blob/HEAD/models/layers/transformer.py","link_basis":"first_harvest_node","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":"fe2a344ff9027718"}},{"code_sha256_prefix":"17837c6365878a53","entry":"MultiHeadAttention","repo":"StonyBrookNLP/deformer","repo_kind":"official","path":"models/layers/transformer.py","file_url":"https://github.com/StonyBrookNLP/deformer/blob/HEAD/models/layers/transformer.py","link_basis":"first_harvest_node","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":"17837c6365878a53"}},{"code_sha256_prefix":"28514670ab26db66","entry":"TransformerLayer","repo":"StonyBrookNLP/deformer","repo_kind":"official","path":"models/layers/transformer.py","file_url":"https://github.com/StonyBrookNLP/deformer/blob/HEAD/models/layers/transformer.py","link_basis":"first_harvest_node","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":"28514670ab26db66"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}