{"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/enhanced-lstm-for-natural-language-inference","title":"Enhanced LSTM for Natural Language Inference","arxiv_id":"1609.06038","date":"2016-09-20","proceeding":"ACL 2017 7","authors":["Qian Chen","Xiaodan Zhu","Zhen-Hua Ling","Si Wei","Hui Jiang","Diana Inkpen"],"abstract":"Reasoning and inference are central to human and artificial intelligence.\nModeling inference in human language is very challenging. With the availability\nof large annotated data (Bowman et al., 2015), it has recently become feasible\nto train neural network based inference models, which have shown to be very\neffective. In this paper, we present a new state-of-the-art result, achieving\nthe accuracy of 88.6% on the Stanford Natural Language Inference Dataset.\nUnlike the previous top models that use very complicated network architectures,\nwe first demonstrate that carefully designing sequential inference models based\non chain LSTMs can outperform all previous models. Based on this, we further\nshow that by explicitly considering recursive architectures in both local\ninference modeling and inference composition, we achieve additional\nimprovement. Particularly, incorporating syntactic parsing information\ncontributes to our best result---it further improves the performance even when\nadded to the already very strong model.","url_abs":"http://arxiv.org/abs/1609.06038v3","url_pdf":"http://arxiv.org/pdf/1609.06038v3.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":"enhanced-lstm-for-natural-language-inference","repo_url":"https://github.com/lukecq1231/nli","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"enhanced-lstm-for-natural-language-inference","repo_url":"https://github.com/Coda-s/BJTU_NLP_Practice","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"enhanced-lstm-for-natural-language-inference","repo_url":"https://github.com/HuihuiChyan/BJTUNLP_Practice2020","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"enhanced-lstm-for-natural-language-inference","repo_url":"https://github.com/HuihuiChyan/BJTUNLP_Practice2021","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"enhanced-lstm-for-natural-language-inference","repo_url":"https://github.com/SJHBXShub/Question_pair","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"enhanced-lstm-for-natural-language-inference","repo_url":"https://github.com/XinyuJiang/fudan_nlp_beginner","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"enhanced-lstm-for-natural-language-inference","repo_url":"https://github.com/blcunlp/CNLI","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"enhanced-lstm-for-natural-language-inference","repo_url":"https://github.com/coetaur0/ESIM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"enhanced-lstm-for-natural-language-inference","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":"enhanced-lstm-for-natural-language-inference","repo_url":"https://github.com/nyu-mll/multiNLI","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"enhanced-lstm-for-natural-language-inference","repo_url":"https://github.com/rockandroll123/natural-language-inference","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"enhanced-lstm-for-natural-language-inference","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":[{"method_slug":"esim","method_name":"ESIM"}],"datasets_introduced":[],"methods_introduced":[{"slug":"esim","name":"ESIM","full_name":"Enhanced Sequential Inference Model"}],"results":[{"leaderboard":"/sota/natural-language-inference-on-snli","task":"Natural Language Inference","dataset":"SNLI","model":"600D ESIM + 300D Syntactic TreeLSTM","rank_in_archive_order":33,"of":98,"metrics":{"% Test Accuracy":"88.6","% Train Accuracy":"93.5","Parameters":"7.7m"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-snli","task":"Natural Language Inference","dataset":"SNLI","model":"Enhanced Sequential Inference Model (Chen et al., [2017a])","rank_in_archive_order":41,"of":98,"metrics":{"% Test Accuracy":"88.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1609.06038","atlas_url":"https://app.syntology.ai/?focus=1609.06038","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}