{"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/attention-modulation-for-zero-shot-cross","title":"Attention Modulation for Zero-Shot Cross-Domain Dialogue State Tracking","arxiv_id":null,"date":"2022-10-01","proceeding":"COLING (CODI, CRAC) 2022 10","authors":["Mathilde Veron","Olivier Galibert","Guillaume Bernard","Sophie Rosset"],"abstract":"Dialog state tracking (DST) is a core step for task-oriented dialogue systems aiming to track the user’s current goal during a dialogue. Recently a special focus has been put on applying existing DST models to new domains, in other words performing zero-shot cross-domain transfer. While recent state-of-the-art models leverage large pre-trained language models, no work has been made on understanding and improving the results of first developed zero-shot models like SUMBT. In this paper, we thus propose to improve SUMBT zero-shot results on MultiWOZ by using attention modulation during inference. This method improves SUMBT zero-shot results significantly on two domains and does not worsen the initial performance with the great advantage of needing no additional training.","url_abs":"https://aclanthology.org/2022.codi-1.11","url_pdf":"https://aclanthology.org/2022.codi-1.11.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":"attention-modulation-for-zero-shot-cross","repo_url":"https://github.com/mathilde-veron/attention-modulation-zero-dst","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"dialogue-state-tracking","task_name":"Dialogue State Tracking"},{"task_slug":"task-oriented-dialogue-systems","task_name":"Task-Oriented Dialogue Systems"},{"task_slug":null,"task_name":"dialog state tracking"}],"methods":[{"method_slug":"dst","method_name":"DST"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}