{"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/a-large-annotated-corpus-for-learning-natural","title":"A large annotated corpus for learning natural language inference","arxiv_id":"1508.05326","date":"2015-08-21","proceeding":"EMNLP 2015 9","authors":["Samuel R. Bowman","Gabor Angeli","Christopher Potts","Christopher D. Manning"],"abstract":"Understanding entailment and contradiction is fundamental to understanding\nnatural language, and inference about entailment and contradiction is a\nvaluable testing ground for the development of semantic representations.\nHowever, machine learning research in this area has been dramatically limited\nby the lack of large-scale resources. To address this, we introduce the\nStanford Natural Language Inference corpus, a new, freely available collection\nof labeled sentence pairs, written by humans doing a novel grounded task based\non image captioning. At 570K pairs, it is two orders of magnitude larger than\nall other resources of its type. This increase in scale allows lexicalized\nclassifiers to outperform some sophisticated existing entailment models, and it\nallows a neural network-based model to perform competitively on natural\nlanguage inference benchmarks for the first time.","url_abs":"http://arxiv.org/abs/1508.05326v1","url_pdf":"http://arxiv.org/pdf/1508.05326v1.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":"a-large-annotated-corpus-for-learning-natural","repo_url":"https://github.com/hpprc/simple-simcse-ja","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"a-large-annotated-corpus-for-learning-natural","repo_url":"https://github.com/kawine/dataset_difficulty","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"a-large-annotated-corpus-for-learning-natural","repo_url":"https://github.com/songyang0716/NLP/tree/master/natural_language_inference/sentence_encoding_RNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[{"slug":"snli","name":"SNLI","full_name":"Stanford Natural Language Inference"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/natural-language-inference-on-snli","task":"Natural Language Inference","dataset":"SNLI","model":"+ Unigram and bigram features","rank_in_archive_order":91,"of":98,"metrics":{"% Test Accuracy":"78.2","% Train Accuracy":"99.7"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-snli","task":"Natural Language Inference","dataset":"SNLI","model":"100D LSTM encoders","rank_in_archive_order":92,"of":98,"metrics":{"% Test Accuracy":"77.6","% Train Accuracy":"84.8","Parameters":"220k"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-snli","task":"Natural Language Inference","dataset":"SNLI","model":"Unlexicalized features","rank_in_archive_order":93,"of":98,"metrics":{"% Test Accuracy":"50.4","% Train Accuracy":"49.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1508.05326","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1508.05326"}},"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/hpprc/simple-simcse-ja","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/songyang0716/NLP/tree/master/natural_language_inference/sentence_encoding_RNN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kawine/dataset_difficulty","reach":null}],"summary":{"ran_draft_wrong":1,"ran_violates":1,"ran_fixture":1},"by_repo_kind":{"listed":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"3d3417580ced96ac","entry":"get_mask","repo":"songyang0716/NLP","repo_kind":"listed","path":"natural_language_inference/ESIM/model.py","file_url":"https://github.com/songyang0716/NLP/blob/HEAD/natural_language_inference/ESIM/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3d3417580ced96ac"}},{"code_sha256_prefix":"926924e03e1d1969","entry":"masked_softmax","repo":"songyang0716/NLP","repo_kind":"listed","path":"natural_language_inference/ESIM/model.py","file_url":"https://github.com/songyang0716/NLP/blob/HEAD/natural_language_inference/ESIM/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"926924e03e1d1969"}},{"code_sha256_prefix":"4fbad937cd67c24b","entry":"weighted_sum","repo":"songyang0716/NLP","repo_kind":"listed","path":"natural_language_inference/ESIM/model.py","file_url":"https://github.com/songyang0716/NLP/blob/HEAD/natural_language_inference/ESIM/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4fbad937cd67c24b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}