{"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/towards-zero-shot-frame-semantic-parsing-for","title":"Towards Zero-Shot Frame Semantic Parsing for Domain Scaling","arxiv_id":"1707.02363","date":"2017-07-07","proceeding":null,"authors":["Ankur Bapna","Gokhan Tur","Dilek Hakkani-Tur","Larry Heck"],"abstract":"State-of-the-art slot filling models for goal-oriented human/machine\nconversational language understanding systems rely on deep learning methods.\nWhile multi-task training of such models alleviates the need for large\nin-domain annotated datasets, bootstrapping a semantic parsing model for a new\ndomain using only the semantic frame, such as the back-end API or knowledge\ngraph schema, is still one of the holy grail tasks of language understanding\nfor dialogue systems. This paper proposes a deep learning based approach that\ncan utilize only the slot description in context without the need for any\nlabeled or unlabeled in-domain examples, to quickly bootstrap a new domain. The\nmain idea of this paper is to leverage the encoding of the slot names and\ndescriptions within a multi-task deep learned slot filling model, to implicitly\nalign slots across domains. The proposed approach is promising for solving the\ndomain scaling problem and eliminating the need for any manually annotated data\nor explicit schema alignment. Furthermore, our experiments on multiple domains\nshow that this approach results in significantly better slot-filling\nperformance when compared to using only in-domain data, especially in the low\ndata regime.","url_abs":"http://arxiv.org/abs/1707.02363v1","url_pdf":"http://arxiv.org/pdf/1707.02363v1.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":"towards-zero-shot-frame-semantic-parsing-for","repo_url":"https://github.com/zliucr/coach","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"semantic-parsing","task_name":"Semantic Parsing"},{"task_slug":"slot-filling","task_name":"Slot Filling"},{"task_slug":"slot-filling-1","task_name":"slot-filling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.02363","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}