{"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/multiway-attention-networks-for-modeling","title":"Multiway Attention Networks for Modeling Sentence Pairs","arxiv_id":null,"date":"2018-07-01","proceeding":"IJCAI 2018 7","authors":["Chuanqi Tan","Furu Wei","Wenhui Wang","Weifeng Lv","Ming Zhou"],"abstract":"Modeling sentence pairs plays the vital role for\r\njudging the relationship between two sentences,\r\nsuch as paraphrase identification, natural language\r\ninference, and answer sentence selection. Previous\r\nwork achieves very promising results using neural\r\nnetworks with attention mechanism. In this paper,\r\nwe propose the multiway attention networks which\r\nemploy multiple attention functions to match sentence pairs under the matching-aggregation framework. Specifically, we design four attention functions to match words in corresponding sentences.\r\nThen, we aggregate the matching information from\r\neach function, and combine the information from\r\nall functions to obtain the final representation. Experimental results demonstrate that the proposed\r\nmultiway attention networks improve the result on\r\nthe Quora Question Pairs, SNLI, MultiNLI, and answer sentence selection task on the SQuAD dataset.","url_abs":"https://www.ijcai.org/proceedings/2018/0613","url_pdf":"https://www.ijcai.org/proceedings/2018/0613.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":"multiway-attention-networks-for-modeling","repo_url":"https://github.com/zsweet/zsw_AI_model","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"paraphrase-identification","task_name":"Paraphrase Identification"},{"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":"150D Multiway Attention Network Ensemble","rank_in_archive_order":18,"of":98,"metrics":{"% Test Accuracy":"89.4","% Train Accuracy":"95.5","Parameters":"58m"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-snli","task":"Natural Language Inference","dataset":"SNLI","model":"150D Multiway Attention Network","rank_in_archive_order":37,"of":98,"metrics":{"% Test Accuracy":"88.3","% Train Accuracy":"94.5","Parameters":"14m"},"uses_additional_data":false},{"leaderboard":"/sota/paraphrase-identification-on-quora-question","task":"Paraphrase Identification","dataset":"Quora Question Pairs","model":"MwAN","rank_in_archive_order":19,"of":31,"metrics":{"Accuracy":"89.12"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}