{"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/reasoning-about-entailment-with-neural","title":"Reasoning about Entailment with Neural Attention","arxiv_id":"1509.06664","date":"2015-09-22","proceeding":null,"authors":["Tim Rocktäschel","Edward Grefenstette","Karl Moritz Hermann","Tomáš Kočiský","Phil Blunsom"],"abstract":"While most approaches to automatically recognizing entailment relations have\nused classifiers employing hand engineered features derived from complex\nnatural language processing pipelines, in practice their performance has been\nonly slightly better than bag-of-word pair classifiers using only lexical\nsimilarity. The only attempt so far to build an end-to-end differentiable\nneural network for entailment failed to outperform such a simple similarity\nclassifier. In this paper, we propose a neural model that reads two sentences\nto determine entailment using long short-term memory units. We extend this\nmodel with a word-by-word neural attention mechanism that encourages reasoning\nover entailments of pairs of words and phrases. Furthermore, we present a\nqualitative analysis of attention weights produced by this model, demonstrating\nsuch reasoning capabilities. On a large entailment dataset this model\noutperforms the previous best neural model and a classifier with engineered\nfeatures by a substantial margin. It is the first generic end-to-end\ndifferentiable system that achieves state-of-the-art accuracy on a textual\nentailment dataset.","url_abs":"http://arxiv.org/abs/1509.06664v4","url_pdf":"http://arxiv.org/pdf/1509.06664v4.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":"reasoning-about-entailment-with-neural","repo_url":"https://github.com/codedecde/Recognizing-Textual-Entailment","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"reasoning-about-entailment-with-neural","repo_url":"https://github.com/dunesand/Text-Matching-based-on-ESIM-model","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"reasoning-about-entailment-with-neural","repo_url":"https://github.com/elkhand/QuoraDuplicates","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"reasoning-about-entailment-with-neural","repo_url":"https://github.com/junfenglx/reasoning_attention","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"reasoning-about-entailment-with-neural","repo_url":"https://github.com/shyamupa/snli-entailment","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"reasoning-about-entailment-with-neural","repo_url":"https://github.com/sunsiqi26/Entailment-with-TensorFlow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"reasoning-about-entailment-with-neural","repo_url":"https://github.com/thomasdic2000/enhancedLSTM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/natural-language-inference-on-snli","task":"Natural Language Inference","dataset":"SNLI","model":"100D LSTMs w/ word-by-word attention","rank_in_archive_order":83,"of":98,"metrics":{"% Test Accuracy":"83.5","% Train Accuracy":"85.3","Parameters":"250k"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1509.06664","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1509.06664"}},"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/thomasdic2000/enhancedLSTM","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/elkhand/QuoraDuplicates","reach":{"status":"ok"}},{"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/dunesand/Text-Matching-based-on-ESIM-model","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/codedecde/Recognizing-Textual-Entailment","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sunsiqi26/Entailment-with-TensorFlow","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shyamupa/snli-entailment","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"24e697458511d16e","entry":"prepare","repo":"junfenglx/reasoning_attention","repo_kind":"listed","path":"snli_reasoning_attention.py","file_url":"https://github.com/junfenglx/reasoning_attention/blob/HEAD/snli_reasoning_attention.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":"24e697458511d16e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}