{"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/answering-complex-questions-using-open","title":"Answering Complex Questions Using Open Information Extraction","arxiv_id":"1704.05572","date":"2017-04-19","proceeding":"ACL 2017 7","authors":["Tushar Khot","Ashish Sabharwal","Peter Clark"],"abstract":"While there has been substantial progress in factoid question-answering (QA),\nanswering complex questions remains challenging, typically requiring both a\nlarge body of knowledge and inference techniques. Open Information Extraction\n(Open IE) provides a way to generate semi-structured knowledge for QA, but to\ndate such knowledge has only been used to answer simple questions with\nretrieval-based methods. We overcome this limitation by presenting a method for\nreasoning with Open IE knowledge, allowing more complex questions to be\nhandled. Using a recently proposed support graph optimization framework for QA,\nwe develop a new inference model for Open IE, in particular one that can work\neffectively with multiple short facts, noise, and the relational structure of\ntuples. Our model significantly outperforms a state-of-the-art structured\nsolver on complex questions of varying difficulty, while also removing the\nreliance on manually curated knowledge.","url_abs":"http://arxiv.org/abs/1704.05572v1","url_pdf":"http://arxiv.org/pdf/1704.05572v1.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":"answering-complex-questions-using-open","repo_url":"https://github.com/allenai/semanticilp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"open-information-extraction","task_name":"Open Information Extraction"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[{"slug":"tupleinf-open-ie-dataset","name":"TupleInf Open IE Dataset","full_name":"TupleInf Open IE Dataset"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1704.05572","atlas_url":"https://app.syntology.ai/?focus=1704.05572","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}