{"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/learned-in-translation-contextualized-word","title":"Learned in Translation: Contextualized Word Vectors","arxiv_id":"1708.00107","date":"2017-08-01","proceeding":"NeurIPS 2017 12","authors":["Bryan McCann","James Bradbury","Caiming Xiong","Richard Socher"],"abstract":"Computer vision has benefited from initializing multiple deep layers with\nweights pretrained on large supervised training sets like ImageNet. Natural\nlanguage processing (NLP) typically sees initialization of only the lowest\nlayer of deep models with pretrained word vectors. In this paper, we use a deep\nLSTM encoder from an attentional sequence-to-sequence model trained for machine\ntranslation (MT) to contextualize word vectors. We show that adding these\ncontext vectors (CoVe) improves performance over using only unsupervised word\nand character vectors on a wide variety of common NLP tasks: sentiment analysis\n(SST, IMDb), question classification (TREC), entailment (SNLI), and question\nanswering (SQuAD). For fine-grained sentiment analysis and entailment, CoVe\nimproves performance of our baseline models to the state of the art.","url_abs":"http://arxiv.org/abs/1708.00107v2","url_pdf":"http://arxiv.org/pdf/1708.00107v2.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":"learned-in-translation-contextualized-word","repo_url":"https://github.com/salesforce/cove","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learned-in-translation-contextualized-word","repo_url":"https://github.com/adi2103/AML-CoVe","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"learned-in-translation-contextualized-word","repo_url":"https://github.com/cove-adml/adml-anon","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"learned-in-translation-contextualized-word","repo_url":"https://github.com/menajosep/AleatoricSent","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"learned-in-translation-contextualized-word","repo_url":"https://github.com/richinkabra/CoVe-BCN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"bilstm","method_name":"BiLSTM"},{"method_slug":"cove","method_name":"CoVe"},{"method_slug":"glove","method_name":"GloVe"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"location-based-attention","method_name":"Location-based Attention"},{"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"}],"datasets_introduced":[],"methods_introduced":[{"slug":"cove","name":"CoVe","full_name":"Contextual Word Vectors"}],"results":[{"leaderboard":"/sota/natural-language-inference-on-snli","task":"Natural Language Inference","dataset":"SNLI","model":"Biattentive Classification Network + CoVe + Char","rank_in_archive_order":38,"of":98,"metrics":{"% Test Accuracy":"88.1","% Train Accuracy":"88.5","Parameters":"22m"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-squad11","task":"Question Answering","dataset":"SQuAD1.1","model":"DCN + Char + CoVe","rank_in_archive_order":152,"of":213,"metrics":{"EM":"71.3","F1":"79.9"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-squad11-dev","task":"Question Answering","dataset":"SQuAD1.1 dev","model":"DCN (Char + CoVe)","rank_in_archive_order":34,"of":55,"metrics":{"EM":"71.3","F1":"79.9"},"uses_additional_data":false},{"leaderboard":"/sota/sentiment-analysis-on-imdb","task":"Sentiment Analysis","dataset":"IMDb","model":"BCN+Char+CoVe","rank_in_archive_order":34,"of":49,"metrics":{"Accuracy":"91.8"},"uses_additional_data":false},{"leaderboard":"/sota/sentiment-analysis-on-sst-2-binary","task":"Sentiment Analysis","dataset":"SST-2 Binary classification","model":"BCN+Char+CoVe","rank_in_archive_order":61,"of":87,"metrics":{"Accuracy":"90.3"},"uses_additional_data":false},{"leaderboard":"/sota/sentiment-analysis-on-sst-5-fine-grained","task":"Sentiment Analysis","dataset":"SST-5 Fine-grained classification","model":"BCN+Char+CoVe","rank_in_archive_order":10,"of":31,"metrics":{"Accuracy":"53.7"},"uses_additional_data":false},{"leaderboard":"/sota/text-classification-on-trec-6","task":"Text Classification","dataset":"TREC-6","model":"CoVe","rank_in_archive_order":9,"of":19,"metrics":{"Error":"4.2"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1708.00107","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.00107"}},"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/menajosep/AleatoricSent","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/richinkabra/CoVe-BCN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/adi2103/AML-CoVe","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/salesforce/cove","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cove-adml/adml-anon","reach":{"status":"unanswered"}}],"summary":{"ran_honours":2,"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":3,"ran":3,"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":"97473786c8952b86","entry":"get_perplexity","repo":"richinkabra/CoVe-BCN","repo_kind":"listed","path":"MTLSTM/train/train_base.py","file_url":"https://github.com/richinkabra/CoVe-BCN/blob/HEAD/MTLSTM/train/train_base.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"97473786c8952b86"}},{"code_sha256_prefix":"ee3ee33169acbe07","entry":"pos_encoding","repo":"adi2103/AML-CoVe","repo_kind":"listed","path":"NMT/Encoder.py","file_url":"https://github.com/adi2103/AML-CoVe/blob/HEAD/NMT/Encoder.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ee3ee33169acbe07"}},{"code_sha256_prefix":"a78b6fff8d3fe895","entry":"read_corpus","repo":"richinkabra/CoVe-BCN","repo_kind":"listed","path":"MTLSTM/train/train_base.py","file_url":"https://github.com/richinkabra/CoVe-BCN/blob/HEAD/MTLSTM/train/train_base.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":"a78b6fff8d3fe895"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}