{"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/decoupling-structure-and-lexicon-for-zero","title":"Decoupling Structure and Lexicon for Zero-Shot Semantic Parsing","arxiv_id":"1804.07918","date":"2018-04-21","proceeding":"EMNLP 2018 10","authors":["Jonathan Herzig","Jonathan Berant"],"abstract":"Building a semantic parser quickly in a new domain is a fundamental challenge\nfor conversational interfaces, as current semantic parsers require expensive\nsupervision and lack the ability to generalize to new domains. In this paper,\nwe introduce a zero-shot approach to semantic parsing that can parse utterances\nin unseen domains while only being trained on examples in other source domains.\nFirst, we map an utterance to an abstract, domain-independent, logical form\nthat represents the structure of the logical form, but contains slots instead\nof KB constants. Then, we replace slots with KB constants via lexical alignment\nscores and global inference. Our model reaches an average accuracy of 53.4% on\n7 domains in the Overnight dataset, substantially better than other zero-shot\nbaselines, and performs as good as a parser trained on over 30% of the target\ndomain examples.","url_abs":"http://arxiv.org/abs/1804.07918v2","url_pdf":"http://arxiv.org/pdf/1804.07918v2.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":"decoupling-structure-and-lexicon-for-zero","repo_url":"https://github.com/jonathanherzig/zero-shot-semantic-parsing","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"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=1804.07918","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}