{"id":167021,"date":"2014-09-01T00:00:00","date_gmt":"2014-09-01T00:00:00","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/msr-research-item\/hypotheses-ranking-for-robust-domain-classification-and-tracking-in-dialogue-systems\/"},"modified":"2018-10-16T21:29:02","modified_gmt":"2018-10-17T04:29:02","slug":"hypotheses-ranking-for-robust-domain-classification-and-tracking-in-dialogue-systems","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/hypotheses-ranking-for-robust-domain-classification-and-tracking-in-dialogue-systems\/","title":{"rendered":"Hypotheses Ranking for Robust Domain Classification And Tracking in Dialogue Systems"},"content":{"rendered":"<div class=\"asset-content\">\n<p>We present a novel application of hypothesis ranking (HR) for the task of domain detection in a multi-domain, multiturn dialog system. Alternate, domain dependent, semantic frames from a spoken language understanding (SLU) analysis are ranked using a gradient boosted decision trees (GBDT) ranker to determine the most likely domain. The ranker, trained using Lambda Rank, makes use of a range of signals derived from the SLU and previous turn context to improve domain detection. On a multi-turn corpus we show that this approach offers accuracy improvements of 3.2% absolute (25.6% relative) compared to relying solely on upfront non-contextual SLU domain models and 2.9% (24.5% relative) improvement even with contextual SLU domain models. We also show that HR can be trained to be robust to changes in the SLU.<\/p>\n<\/div>\n<p><!-- .asset-content --><\/p>\n","protected":false},"excerpt":{"rendered":"<p>We present a novel application of hypothesis ranking (HR) for the task of domain detection in a multi-domain, multiturn dialog system. Alternate, domain dependent, semantic frames from a spoken language understanding (SLU) analysis are ranked using a gradient boosted decision trees (GBDT) ranker to determine the most likely domain. The ranker, trained using Lambda Rank, [&hellip;]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[13556,13554],"msr-publication-type":[193716],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-field-of-study":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-167021","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-research-area-human-computer-interaction","msr-locale-en_us"],"msr_publishername":"ISCA - International Speech Communication Association","msr_edition":"Proceedings of the 15th Annual Conference of the International Speech Communication Association (INTERSPEECH 2014)","msr_affiliation":"","msr_published_date":"2014-09-01","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"Proceedings of the 15th Annual Conference of the International Speech Communication Association (INTERSPEECH 2014)","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":"217444","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","title":"IS14.HR.final_photoready.pdf","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2014\/09\/IS14.HR_.final_photoready.pdf","id":217444,"label_id":0}],"msr_related_uploader":"","msr_attachments":[{"id":217444,"url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2014\/09\/IS14.HR_.final_photoready.pdf"}],"msr-author-ordering":[{"type":"user_nicename","value":"jerobich","user_id":32241,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=jerobich"},{"type":"user_nicename","value":"pacrook","user_id":33177,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=pacrook"},{"type":"text","value":"Puyang Xu","user_id":0,"rest_url":false},{"type":"user_nicename","value":"omkhan","user_id":33161,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=omkhan"},{"type":"user_nicename","value":"rusarika","user_id":33472,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=rusarika"}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[],"msr_project":[171313],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/167021"}],"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\/167021\/revisions"}],"predecessor-version":[{"id":536280,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/167021\/revisions\/536280"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=167021"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=167021"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=167021"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=167021"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=167021"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=167021"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=167021"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=167021"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=167021"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=167021"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=167021"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=167021"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=167021"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=167021"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=167021"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}