{"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/leveraging-slot-descriptions-for-zero-shot","title":"Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue State Tracking","arxiv_id":"2105.04222","date":"2021-05-10","proceeding":null,"authors":["Zhaojiang Lin","Bing Liu","Seungwhan Moon","Paul Crook","Zhenpeng Zhou","Zhiguang Wang","Zhou Yu","Andrea Madotto","Eunjoon Cho","Rajen Subba"],"abstract":"Zero-shot cross-domain dialogue state tracking (DST) enables us to handle task-oriented dialogue in unseen domains without the expense of collecting in-domain data. In this paper, we propose a slot description enhanced generative approach for zero-shot cross-domain DST. Specifically, our model first encodes dialogue context and slots with a pre-trained self-attentive encoder, and generates slot values in an auto-regressive manner. In addition, we incorporate Slot Type Informed Descriptions that capture the shared information across slots to facilitate cross-domain knowledge transfer. Experimental results on the MultiWOZ dataset show that our proposed method significantly improves existing state-of-the-art results in the zero-shot cross-domain setting.","url_abs":"https://arxiv.org/abs/2105.04222v1","url_pdf":"https://arxiv.org/pdf/2105.04222v1.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":"leveraging-slot-descriptions-for-zero-shot","repo_url":"https://github.com/facebookresearch/Zero-Shot-DST","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"leveraging-slot-descriptions-for-zero-shot","repo_url":"https://github.com/devjwsong/t5-dst-modified-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"dialogue-state-tracking","task_name":"Dialogue State Tracking"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"dst","method_name":"DST"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2105.04222","atlas_url":"https://app.syntology.ai/?focus=2105.04222","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}