{"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/multi-task-deep-neural-networks-for-natural","title":"Multi-Task Deep Neural Networks for Natural Language Understanding","arxiv_id":"1901.11504","date":"2019-01-31","proceeding":"ACL 2019 7","authors":["Xiaodong Liu","Pengcheng He","Weizhu Chen","Jianfeng Gao"],"abstract":"In this paper, we present a Multi-Task Deep Neural Network (MT-DNN) for learning representations across multiple natural language understanding (NLU) tasks. MT-DNN not only leverages large amounts of cross-task data, but also benefits from a regularization effect that leads to more general representations in order to adapt to new tasks and domains. MT-DNN extends the model proposed in Liu et al. (2015) by incorporating a pre-trained bidirectional transformer language model, known as BERT (Devlin et al., 2018). MT-DNN obtains new state-of-the-art results on ten NLU tasks, including SNLI, SciTail, and eight out of nine GLUE tasks, pushing the GLUE benchmark to 82.7% (2.2% absolute improvement). We also demonstrate using the SNLI and SciTail datasets that the representations learned by MT-DNN allow domain adaptation with substantially fewer in-domain labels than the pre-trained BERT representations. The code and pre-trained models are publicly available at https://github.com/namisan/mt-dnn.","url_abs":"https://arxiv.org/abs/1901.11504v2","url_pdf":"https://arxiv.org/pdf/1901.11504v2.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":"multi-task-deep-neural-networks-for-natural","repo_url":"https://github.com/namisan/mt-dnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-task-deep-neural-networks-for-natural","repo_url":"https://github.com/ABaldrati/MT-BERT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-task-deep-neural-networks-for-natural","repo_url":"https://github.com/gaohuan2015/NLPTool","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"multi-task-deep-neural-networks-for-natural","repo_url":"https://github.com/om00839/machine-suneung","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"multi-task-deep-neural-networks-for-natural","repo_url":"https://github.com/phueb/BabyBertSRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"multi-task-deep-neural-networks-for-natural","repo_url":"https://github.com/phueb/CHILDES-SRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"multi-task-deep-neural-networks-for-natural","repo_url":"https://github.com/xycforgithub/MultiTask-MRC","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"linguistic-acceptability","task_name":"Linguistic Acceptability"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"paraphrase-identification","task_name":"Paraphrase Identification"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"}],"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":"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":"softmax","method_name":"Softmax"},{"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":[{"leaderboard":"/sota/linguistic-acceptability-on-cola","task":"Linguistic Acceptability","dataset":"CoLA","model":"MT-DNN","rank_in_archive_order":18,"of":43,"metrics":{"Accuracy":"68.4%"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-multinli","task":"Natural Language Inference","dataset":"MultiNLI","model":"MT-DNN","rank_in_archive_order":24,"of":67,"metrics":{"Matched":"86.7","Mismatched":"86.0"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-snli","task":"Natural Language Inference","dataset":"SNLI","model":"MT-DNN","rank_in_archive_order":10,"of":98,"metrics":{"% Test Accuracy":"91.6","% Train Accuracy":"97.2","Parameters":"330m"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-snli","task":"Natural Language Inference","dataset":"SNLI","model":"Ntumpha","rank_in_archive_order":12,"of":98,"metrics":{"% Test Accuracy":"90.5","% Train Accuracy":"99.1","Parameters":"220"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-scitail","task":"Natural Language Inference","dataset":"SciTail","model":"MT-DNN","rank_in_archive_order":2,"of":13,"metrics":{"Accuracy":"94.1"},"uses_additional_data":false},{"leaderboard":"/sota/paraphrase-identification-on-quora-question","task":"Paraphrase Identification","dataset":"Quora Question Pairs","model":"MT-DNN","rank_in_archive_order":10,"of":31,"metrics":{"Accuracy":"89.6","F1":"72.4"},"uses_additional_data":false},{"leaderboard":"/sota/sentiment-analysis-on-sst-2-binary","task":"Sentiment Analysis","dataset":"SST-2 Binary classification","model":"MT-DNN","rank_in_archive_order":22,"of":87,"metrics":{"Accuracy":"95.6"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1901.11504","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.11504"}},"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/phueb/BabyBertSRL","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gaohuan2015/NLPTool","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/namisan/mt-dnn","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/om00839/machine-suneung","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ABaldrati/MT-BERT","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xycforgithub/MultiTask-MRC","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/phueb/CHILDES-SRL","reach":{"status":"ok"}}],"summary":{"ran_honours":1,"ran_draft_wrong":3,"ran_violates":1,"unverified":8},"by_repo_kind":{"listed":{"samples":13,"ran":5,"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":2,"samples":[{"code_sha256_prefix":"691b566282a42d88","entry":"linear","repo":"xycforgithub/MultiTask-MRC","repo_kind":"listed","path":"src/common.py","file_url":"https://github.com/xycforgithub/MultiTask-MRC/blob/HEAD/src/common.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"691b566282a42d88"}},{"code_sha256_prefix":"ec4448373d72d636","entry":"precook","repo":"xycforgithub/MultiTask-MRC","repo_kind":"listed","path":"my_utils/bleu_scorer.py","file_url":"https://github.com/xycforgithub/MultiTask-MRC/blob/HEAD/my_utils/bleu_scorer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"ec4448373d72d636"}},{"code_sha256_prefix":"235ffc8c67133e68","entry":"retry_with_batchsize_halving","repo":"ABaldrati/MT-BERT","repo_kind":"listed","path":"train_glue.py","file_url":"https://github.com/ABaldrati/MT-BERT/blob/HEAD/train_glue.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":"235ffc8c67133e68"}},{"code_sha256_prefix":"b686437952d7aa47","entry":"split_n","repo":"ABaldrati/MT-BERT","repo_kind":"listed","path":"train_glue.py","file_url":"https://github.com/ABaldrati/MT-BERT/blob/HEAD/train_glue.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b686437952d7aa47"}},{"code_sha256_prefix":"248284f69adfeaad","entry":"str2bool","repo":"xycforgithub/MultiTask-MRC","repo_kind":"listed","path":"config.py","file_url":"https://github.com/xycforgithub/MultiTask-MRC/blob/HEAD/config.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"248284f69adfeaad"}},{"code_sha256_prefix":"ed169d65a4e1896a","entry":"activation","repo":"xycforgithub/MultiTask-MRC","repo_kind":"listed","path":"src/common.py","file_url":"https://github.com/xycforgithub/MultiTask-MRC/blob/HEAD/src/common.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":"ed169d65a4e1896a"}},{"code_sha256_prefix":"7586e1d32f7325f7","entry":"cook_refs","repo":"xycforgithub/MultiTask-MRC","repo_kind":"listed","path":"my_utils/bleu_scorer.py","file_url":"https://github.com/xycforgithub/MultiTask-MRC/blob/HEAD/my_utils/bleu_scorer.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":"7586e1d32f7325f7"}},{"code_sha256_prefix":"019ae8bc6f98133f","entry":"cook_test","repo":"xycforgithub/MultiTask-MRC","repo_kind":"listed","path":"my_utils/bleu_scorer.py","file_url":"https://github.com/xycforgithub/MultiTask-MRC/blob/HEAD/my_utils/bleu_scorer.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":"019ae8bc6f98133f"}},{"code_sha256_prefix":"f80bedbbd1203629","entry":"data_config","repo":"xycforgithub/MultiTask-MRC","repo_kind":"listed","path":"config.py","file_url":"https://github.com/xycforgithub/MultiTask-MRC/blob/HEAD/config.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":"f80bedbbd1203629"}},{"code_sha256_prefix":"ca57925dc461ab4a","entry":"init_wrapper","repo":"xycforgithub/MultiTask-MRC","repo_kind":"listed","path":"src/common.py","file_url":"https://github.com/xycforgithub/MultiTask-MRC/blob/HEAD/src/common.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":"ca57925dc461ab4a"}},{"code_sha256_prefix":"4dde989e875a2f0a","entry":"load_data","repo":"xycforgithub/MultiTask-MRC","repo_kind":"listed","path":"prepro.py","file_url":"https://github.com/xycforgithub/MultiTask-MRC/blob/HEAD/prepro.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":"4dde989e875a2f0a"}},{"code_sha256_prefix":"08a4c368c95d9755","entry":"model_config","repo":"xycforgithub/MultiTask-MRC","repo_kind":"listed","path":"config.py","file_url":"https://github.com/xycforgithub/MultiTask-MRC/blob/HEAD/config.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":"08a4c368c95d9755"}},{"code_sha256_prefix":"bf7527cf0e0955a9","entry":"postag_func","repo":"xycforgithub/MultiTask-MRC","repo_kind":"listed","path":"prepro.py","file_url":"https://github.com/xycforgithub/MultiTask-MRC/blob/HEAD/prepro.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":"bf7527cf0e0955a9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}