{"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/modelling-interaction-of-sentence-pair-with","title":"Modelling Interaction of Sentence Pair with coupled-LSTMs","arxiv_id":"1605.05573","date":"2016-05-18","proceeding":"EMNLP 2016 11","authors":["Pengfei Liu","Xipeng Qiu","Xuanjing Huang"],"abstract":"Recently, there is rising interest in modelling the interactions of two\nsentences with deep neural networks. However, most of the existing methods\nencode two sequences with separate encoders, in which a sentence is encoded\nwith little or no information from the other sentence. In this paper, we\npropose a deep architecture to model the strong interaction of sentence pair\nwith two coupled-LSTMs. Specifically, we introduce two coupled ways to model\nthe interdependences of two LSTMs, coupling the local contextualized\ninteractions of two sentences. We then aggregate these interactions and use a\ndynamic pooling to select the most informative features. Experiments on two\nvery large datasets demonstrate the efficacy of our proposed architecture and\nits superiority to state-of-the-art methods.","url_abs":"http://arxiv.org/abs/1605.05573v2","url_pdf":"http://arxiv.org/pdf/1605.05573v2.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":[],"tasks":[{"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":"50D stacked TC-LSTMs","rank_in_archive_order":73,"of":98,"metrics":{"% Test Accuracy":"85.1","% Train Accuracy":"86.7","Parameters":"190k"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}