{"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/inferring-logical-forms-from-denotations","title":"Inferring Logical Forms From Denotations","arxiv_id":"1606.06900","date":"2016-06-22","proceeding":"ACL 2016 8","authors":["Panupong Pasupat","Percy Liang"],"abstract":"A core problem in learning semantic parsers from denotations is picking out\nconsistent logical forms--those that yield the correct denotation--from a\ncombinatorially large space. To control the search space, previous work relied\non restricted set of rules, which limits expressivity. In this paper, we\nconsider a much more expressive class of logical forms, and show how to use\ndynamic programming to efficiently represent the complete set of consistent\nlogical forms. Expressivity also introduces many more spurious logical forms\nwhich are consistent with the correct denotation but do not represent the\nmeaning of the utterance. To address this, we generate fictitious worlds and\nuse crowdsourced denotations on these worlds to filter out spurious logical\nforms. On the WikiTableQuestions dataset, we increase the coverage of\nanswerable questions from 53.5% to 76%, and the additional crowdsourced\nsupervision lets us rule out 92.1% of spurious logical forms.","url_abs":"http://arxiv.org/abs/1606.06900v2","url_pdf":"http://arxiv.org/pdf/1606.06900v2.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":"inferring-logical-forms-from-denotations","repo_url":"https://github.com/percyliang/sempre","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"inferring-logical-forms-from-denotations","repo_url":"https://worksheets.codalab.org/worksheets/0x47cc64d9c8ba4a878807c7c35bb22a42","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1606.06900","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}