{"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/unsupervised-deep-structured-semantic-models","title":"Unsupervised Deep Structured Semantic Models for Commonsense Reasoning","arxiv_id":"1904.01938","date":"2019-04-03","proceeding":"NAACL 2019 6","authors":["Shuohang Wang","Sheng Zhang","Yelong Shen","Xiaodong Liu","Jingjing Liu","Jianfeng Gao","Jing Jiang"],"abstract":"Commonsense reasoning is fundamental to natural language understanding. While\ntraditional methods rely heavily on human-crafted features and knowledge bases,\nwe explore learning commonsense knowledge from a large amount of raw text via\nunsupervised learning. We propose two neural network models based on the Deep\nStructured Semantic Models (DSSM) framework to tackle two classic commonsense\nreasoning tasks, Winograd Schema challenges (WSC) and Pronoun Disambiguation\n(PDP). Evaluation shows that the proposed models effectively capture contextual\ninformation in the sentence and co-reference information between pronouns and\nnouns, and achieve significant improvement over previous state-of-the-art\napproaches.","url_abs":"http://arxiv.org/abs/1904.01938v1","url_pdf":"http://arxiv.org/pdf/1904.01938v1.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":"common-sense-reasoning","task_name":"Common Sense Reasoning"},{"task_slug":"coreference-resolution","task_name":"Coreference Resolution"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/coreference-resolution-on-winograd-schema","task":"Coreference Resolution","dataset":"Winograd Schema Challenge","model":"DSSM","rank_in_archive_order":47,"of":82,"metrics":{"Accuracy":"63.0"},"uses_additional_data":false},{"leaderboard":"/sota/coreference-resolution-on-winograd-schema","task":"Coreference Resolution","dataset":"Winograd Schema Challenge","model":"UDSSM-II (ensemble)","rank_in_archive_order":50,"of":82,"metrics":{"Accuracy":"62.4"},"uses_additional_data":false},{"leaderboard":"/sota/coreference-resolution-on-winograd-schema","task":"Coreference Resolution","dataset":"Winograd Schema Challenge","model":"UDSSM-II","rank_in_archive_order":60,"of":82,"metrics":{"Accuracy":"59.2"},"uses_additional_data":false},{"leaderboard":"/sota/coreference-resolution-on-winograd-schema","task":"Coreference Resolution","dataset":"Winograd Schema Challenge","model":"UDSSM-I (ensemble)","rank_in_archive_order":65,"of":82,"metrics":{"Accuracy":"57.1"},"uses_additional_data":false},{"leaderboard":"/sota/coreference-resolution-on-winograd-schema","task":"Coreference Resolution","dataset":"Winograd Schema Challenge","model":"UDSSM-I","rank_in_archive_order":72,"of":82,"metrics":{"Accuracy":"54.5"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-understanding-on-pdp60","task":"Natural Language Understanding","dataset":"PDP60","model":"UDSSM-II (ensemble)","rank_in_archive_order":3,"of":13,"metrics":{"Accuracy":"78.3"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-understanding-on-pdp60","task":"Natural Language Understanding","dataset":"PDP60","model":"UDSSM-I (ensemble)","rank_in_archive_order":4,"of":13,"metrics":{"Accuracy":"76.7"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-understanding-on-pdp60","task":"Natural Language Understanding","dataset":"PDP60","model":"DSSM","rank_in_archive_order":5,"of":13,"metrics":{"Accuracy":"75.0"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-understanding-on-pdp60","task":"Natural Language Understanding","dataset":"PDP60","model":"UDSSM-II","rank_in_archive_order":6,"of":13,"metrics":{"Accuracy":"75"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.01938","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}