{"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/learning-natural-language-inference-with-lstm","title":"Learning Natural Language Inference with LSTM","arxiv_id":"1512.08849","date":"2015-12-30","proceeding":"NAACL 2016 6","authors":["Shuohang Wang","Jing Jiang"],"abstract":"Natural language inference (NLI) is a fundamentally important task in natural\nlanguage processing that has many applications. The recently released Stanford\nNatural Language Inference (SNLI) corpus has made it possible to develop and\nevaluate learning-centered methods such as deep neural networks for natural\nlanguage inference (NLI). In this paper, we propose a special long short-term\nmemory (LSTM) architecture for NLI. Our model builds on top of a recently\nproposed neural attention model for NLI but is based on a significantly\ndifferent idea. Instead of deriving sentence embeddings for the premise and the\nhypothesis to be used for classification, our solution uses a match-LSTM to\nperform word-by-word matching of the hypothesis with the premise. This LSTM is\nable to place more emphasis on important word-level matching results. In\nparticular, we observe that this LSTM remembers important mismatches that are\ncritical for predicting the contradiction or the neutral relationship label. On\nthe SNLI corpus, our model achieves an accuracy of 86.1%, outperforming the\nstate of the art.","url_abs":"http://arxiv.org/abs/1512.08849v2","url_pdf":"http://arxiv.org/pdf/1512.08849v2.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":"learning-natural-language-inference-with-lstm","repo_url":"https://github.com/shuohangwang/SeqMatchSeq","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok"}},{"paper_slug":"learning-natural-language-inference-with-lstm","repo_url":"https://github.com/donghyeonk/match-lstm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-natural-language-inference-with-lstm","repo_url":"https://github.com/fuhuamosi/MatchLstm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"learning-natural-language-inference-with-lstm","repo_url":"https://github.com/junfenglx/reasoning_attention","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-embeddings","task_name":"Sentence Embeddings"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/natural-language-inference-on-snli","task":"Natural Language Inference","dataset":"SNLI","model":"300D mLSTM word-by-word attention model","rank_in_archive_order":61,"of":98,"metrics":{"% Test Accuracy":"86.1","% Train Accuracy":"92.0","Parameters":"1.9m"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1512.08849","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1512.08849"}},"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/junfenglx/reasoning_attention","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shuohangwang/SeqMatchSeq","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/donghyeonk/match-lstm","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/fuhuamosi/MatchLstm","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{},"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":"24e697458511d16e","entry":"prepare","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"24e697458511d16e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}