{"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/neural-semantic-parsing-over-multiple","title":"Neural Semantic Parsing over Multiple Knowledge-bases","arxiv_id":"1702.01569","date":"2017-02-06","proceeding":"ACL 2017 7","authors":["Jonathan Herzig","Jonathan Berant"],"abstract":"A fundamental challenge in developing semantic parsers is the paucity of\nstrong supervision in the form of language utterances annotated with logical\nform. In this paper, we propose to exploit structural regularities in language\nin different domains, and train semantic parsers over multiple knowledge-bases\n(KBs), while sharing information across datasets. We find that we can\nsubstantially improve parsing accuracy by training a single\nsequence-to-sequence model over multiple KBs, when providing an encoding of the\ndomain at decoding time. Our model achieves state-of-the-art performance on the\nOvernight dataset (containing eight domains), improves performance over a\nsingle KB baseline from 75.6% to 79.6%, while obtaining a 7x reduction in the\nnumber of model parameters.","url_abs":"http://arxiv.org/abs/1702.01569v2","url_pdf":"http://arxiv.org/pdf/1702.01569v2.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":"neural-semantic-parsing-over-multiple","repo_url":"https://worksheets.codalab.org/worksheets/0xdec998f58deb4829aba80fbf49f69236","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"form","task_name":"Form"},{"task_slug":"semantic-parsing","task_name":"Semantic Parsing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1702.01569","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}