{"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/open-vocabulary-semantic-parsing-with-both","title":"Open-Vocabulary Semantic Parsing with both Distributional Statistics and Formal Knowledge","arxiv_id":"1607.03542","date":"2016-07-12","proceeding":null,"authors":["Matt Gardner","Jayant Krishnamurthy"],"abstract":"Traditional semantic parsers map language onto compositional, executable\nqueries in a fixed schema. This mapping allows them to effectively leverage the\ninformation contained in large, formal knowledge bases (KBs, e.g., Freebase) to\nanswer questions, but it is also fundamentally limiting---these semantic\nparsers can only assign meaning to language that falls within the KB's\nmanually-produced schema. Recently proposed methods for open vocabulary\nsemantic parsing overcome this limitation by learning execution models for\narbitrary language, essentially using a text corpus as a kind of knowledge\nbase. However, all prior approaches to open vocabulary semantic parsing replace\na formal KB with textual information, making no use of the KB in their models.\nWe show how to combine the disparate representations used by these two\napproaches, presenting for the first time a semantic parser that (1) produces\ncompositional, executable representations of language, (2) can successfully\nleverage the information contained in both a formal KB and a large corpus, and\n(3) is not limited to the schema of the underlying KB. We demonstrate\nsignificantly improved performance over state-of-the-art baselines on an\nopen-domain natural language question answering task.","url_abs":"http://arxiv.org/abs/1607.03542v2","url_pdf":"http://arxiv.org/pdf/1607.03542v2.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":"open-vocabulary-semantic-parsing-with-both","repo_url":"https://github.com/allenai/open_vocab_semparse","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"semantic-parsing","task_name":"Semantic Parsing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}