{"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/recurrent-neural-network-based-sentence","title":"Recurrent Neural Network-Based Sentence Encoder with Gated Attention for Natural Language Inference","arxiv_id":"1708.01353","date":"2017-08-04","proceeding":"WS 2017 9","authors":["Qian Chen","Xiaodan Zhu","Zhen-Hua Ling","Si Wei","Hui Jiang","Diana Inkpen"],"abstract":"The RepEval 2017 Shared Task aims to evaluate natural language understanding\nmodels for sentence representation, in which a sentence is represented as a\nfixed-length vector with neural networks and the quality of the representation\nis tested with a natural language inference task. This paper describes our\nsystem (alpha) that is ranked among the top in the Shared Task, on both the\nin-domain test set (obtaining a 74.9% accuracy) and on the cross-domain test\nset (also attaining a 74.9% accuracy), demonstrating that the model generalizes\nwell to the cross-domain data. Our model is equipped with intra-sentence\ngated-attention composition which helps achieve a better performance. In\naddition to submitting our model to the Shared Task, we have also tested it on\nthe Stanford Natural Language Inference (SNLI) dataset. We obtain an accuracy\nof 85.5%, which is the best reported result on SNLI when cross-sentence\nattention is not allowed, the same condition enforced in RepEval 2017.","url_abs":"http://arxiv.org/abs/1708.01353v1","url_pdf":"http://arxiv.org/pdf/1708.01353v1.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":"recurrent-neural-network-based-sentence","repo_url":"https://github.com/lukecq1231/enc_nli","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"recurrent-neural-network-based-sentence","repo_url":"https://github.com/eilon47/DL_Ass4","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/natural-language-inference-on-snli","task":"Natural Language Inference","dataset":"SNLI","model":"600D (300+300) Deep Gated Attn. BiLSTM encoders","rank_in_archive_order":71,"of":98,"metrics":{"% Test Accuracy":"85.5","% Train Accuracy":"90.5","Parameters":"12m"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1708.01353","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}