{"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/compositional-semantic-parsing-on-semi","title":"Compositional Semantic Parsing on Semi-Structured Tables","arxiv_id":"1508.00305","date":"2015-08-03","proceeding":"IJCNLP 2015 7","authors":["Panupong Pasupat","Percy Liang"],"abstract":"Two important aspects of semantic parsing for question answering are the\nbreadth of the knowledge source and the depth of logical compositionality.\nWhile existing work trades off one aspect for another, this paper\nsimultaneously makes progress on both fronts through a new task: answering\ncomplex questions on semi-structured tables using question-answer pairs as\nsupervision. The central challenge arises from two compounding factors: the\nbroader domain results in an open-ended set of relations, and the deeper\ncompositionality results in a combinatorial explosion in the space of logical\nforms. We propose a logical-form driven parsing algorithm guided by strong\ntyping constraints and show that it obtains significant improvements over\nnatural baselines. For evaluation, we created a new dataset of 22,033 complex\nquestions on Wikipedia tables, which is made publicly available.","url_abs":"http://arxiv.org/abs/1508.00305v1","url_pdf":"http://arxiv.org/pdf/1508.00305v1.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":"compositional-semantic-parsing-on-semi","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":"compositional-semantic-parsing-on-semi","repo_url":"https://worksheets.codalab.org/worksheets/0xf26cd79d4d734287868923ad1067cf4c","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"compositional-semantic-parsing-on-semi","repo_url":"https://github.com/microsoft/BIPIA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"compositional-semantic-parsing-on-semi","repo_url":"https://github.com/ppasupat/WikiTableQuestions","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"CC-BY-SA-4.0"}}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"semantic-parsing","task_name":"Semantic Parsing"}],"methods":[],"datasets_introduced":[{"slug":"wikitablequestions","name":"WikiTableQuestions","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1508.00305","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}