{"id":165256,"date":"2013-08-01T00:00:00","date_gmt":"2013-08-01T00:00:00","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/msr-research-item\/multi-domain-learning-and-generalization-in-dialog-state-tracking\/"},"modified":"2018-10-16T21:53:33","modified_gmt":"2018-10-17T04:53:33","slug":"multi-domain-learning-and-generalization-in-dialog-state-tracking","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/multi-domain-learning-and-generalization-in-dialog-state-tracking\/","title":{"rendered":"Multi-Domain Learning and Generalization In Dialog State Tracking"},"content":{"rendered":"<div class=\"asset-content\">\n<p>Statistical approaches to dialog state tracking synthesize information across multiple turns in the dialog, overcoming some speech recognition errors. When training a dialog state tracker, there is typically only a small corpus of well-matched dialog data available. However, often there is a large corpus of mismatched but related data \u2013 perhaps pertaining to different semantic concepts, or from a different dialog system. It would be desirable to use this related dialog data to supplement the small corpus of well-matched dialog data. This paper addresses this task as multi-domain learning, presenting 3 methods which synthesize data from different slots and different dialog systems. Since deploying a new dialog state tracker often changes the resulting dialogs in ways that are difficult to predict, we study how well each method generalizes to unseen distributions of dialog data. Our main result is the finding that a simple method for multi-domain learning substantially improves performance in highly mismatched conditions.<\/p>\n<\/div>\n<p><!-- .asset-content --><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Statistical approaches to dialog state tracking synthesize information across multiple turns in the dialog, overcoming some speech recognition errors. When training a dialog state tracker, there is typically only a small corpus of well-matched dialog data available. However, often there is a large corpus of mismatched but related data \u2013 perhaps pertaining to different semantic [&hellip;]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","footnotes":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[13554],"msr-publication-type":[193716],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-165256","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-human-computer-interaction","msr-locale-en_us"],"msr_publishername":"Association for Computational Linguistics","msr_edition":"Proceedings of the SIGDIAL 2013 Conference, Metz, France","msr_affiliation":"","msr_published_date":"2013-08-01","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":1,"msr_main_download":"205329","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","title":"williams2013sigdial.pdf","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/02\/williams2013sigdial.pdf","id":205329,"label_id":0}],"msr_related_uploader":"","msr_attachments":[{"id":205329,"url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/02\/williams2013sigdial.pdf"}],"msr-author-ordering":[{"type":"user_nicename","value":"jawillia","user_id":32190,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=jawillia"}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[],"msr_project":[393245,171313],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","related_content":{"projects":[{"ID":393245,"post_title":"Conversational Intelligence","post_name":"conversational-intelligence","post_type":"msr-project","post_date":"2017-07-05 10:01:45","post_modified":"2017-11-15 13:39:25","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/conversational-intelligence\/","post_excerpt":"Intelligent agents that can handle human language play a growing role in personalized, ubiquitous computing and the everyday use of devices. Agents need to be able to communicate and collaborate with humans in ways that are seamless and natural, and to be able to learn new behaviors, concepts, and relationships as first-class operations. In other words, our devices need to be able to converse with us. In this project, Microsoft Research AI teams are interested&hellip;","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/393245"}]}},{"ID":171313,"post_title":"Dialog and Conversational Systems Research","post_name":"dialog-and-conversational-systems-research","post_type":"msr-project","post_date":"2014-03-14 09:46:35","post_modified":"2017-07-11 15:34:26","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/dialog-and-conversational-systems-research\/","post_excerpt":"Conversational systems interact with people through language to assist, enable, or entertain. Research at Microsoft spans dialogs that use language exclusively, or in conjunctions with additional modalities like gesture; where language is spoken or in text; and in a variety of settings, such as conversational systems in apps or devices, and situated interactions in the real world. Projects Spoken Language Understanding","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/171313"}]}}]},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/165256","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":2,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/165256\/revisions"}],"predecessor-version":[{"id":400364,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/165256\/revisions\/400364"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=165256"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=165256"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=165256"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=165256"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=165256"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=165256"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=165256"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=165256"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=165256"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=165256"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=165256"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=165256"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=165256"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=165256"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=165256"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=165256"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}