{"id":164154,"date":"2012-12-01T00:00:00","date_gmt":"2012-12-01T00:00:00","guid":{"rendered":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/msr-research-item\/challenges-and-opportunities-for-state-tracking-in-statistical-spoken-dialog-systems-results-from-two-public-deployments\/"},"modified":"2018-10-16T20:07:23","modified_gmt":"2018-10-17T03:07:23","slug":"challenges-and-opportunities-for-state-tracking-in-statistical-spoken-dialog-systems-results-from-two-public-deployments","status":"publish","type":"msr-research-item","link":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/publication\/challenges-and-opportunities-for-state-tracking-in-statistical-spoken-dialog-systems-results-from-two-public-deployments\/","title":{"rendered":"Challenges and Opportunities for State Tracking in Statistical Spoken Dialog Systems: Results From Two Public Deployments"},"content":{"rendered":"<div class=\"asset-content\">\n<p>Whereas traditional dialog systems operate on the top ASR hypothesis, statistical dialog systems claim to be more robust to ASR errors by maintaining a distribution over multiple hidden dialog states. Recently, these techniques have been deployed publicly for the first time, making empirical measurements possible. In this paper, we analyze two of these deployments. We find that performance was quite mixed: in some cases statistical techniques improved accuracy with respect to the top speech recognition hypothesis; in other cases, accuracy was degraded. Investigating degradations, we find the three main causes are (non-obviously) inaccurate parameter estimates, poor confidence scores, and correlations in speech recognition errors. Overall the results suggest fundamental weaknesses in the formulation as a generative model, and we suggest alternatives as future work.<\/p>\n<\/div>\n<p><!-- .asset-content --><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Whereas traditional dialog systems operate on the top ASR hypothesis, statistical dialog systems claim to be more robust to ASR errors by maintaining a distribution over multiple hidden dialog states. Recently, these techniques have been deployed publicly for the first time, making empirical measurements possible. In this paper, we analyze two of these deployments. We [&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":"","msr-author-ordering":[{"type":"user_nicename","value":"jawillia"}],"msr_publishername":"IEEE SPS","msr_publisher_other":"","msr_booktitle":"","msr_chapter":"","msr_edition":"IEEE Journal of Selected Topics in Signal Processing","msr_editors":"","msr_how_published":"","msr_isbn":"","msr_issue":"","msr_journal":"IEEE Journal of Selected Topics in Signal Processing","msr_number":"8","msr_organization":"","msr_pages_string":"959-970","msr_page_range_start":"959","msr_page_range_end":"970","msr_series":"","msr_volume":"6","msr_copyright":"","msr_conference_name":"","msr_doi":"","msr_arxiv_id":"","msr_s2_paper_id":"","msr_mag_id":"","msr_pubmed_id":"","msr_other_authors":"","msr_other_contributors":"","msr_speaker":"","msr_award":"","msr_affiliation":"","msr_institution":"","msr_host":"","msr_version":"","msr_duration":"","msr_original_fields_of_study":"","msr_release_tracker_id":"","msr_s2_match_type":"","msr_citation_count_updated":"","msr_published_date":"2012-12-01","msr_highlight_text":"","msr_notes":"","msr_longbiography":"","msr_publicationurl":"","msr_external_url":"","msr_secondary_video_url":"","msr_conference_url":"","msr_journal_url":"","msr_s2_pdf_url":"","msr_year":2012,"msr_citation_count":0,"msr_influential_citations":0,"msr_reference_count":0,"msr_s2_match_confidence":0,"msr_microsoftintellectualproperty":true,"msr_s2_open_access":false,"msr_s2_author_ids":[],"msr_pub_ids":[],"msr_hide_image_in_river":0,"footnotes":""},"msr-research-highlight":[],"research-area":[13554],"msr-publication-type":[193715],"msr-publisher":[],"msr-focus-area":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-164154","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-human-computer-interaction","msr-locale-en_us"],"msr_publishername":"IEEE SPS","msr_edition":"IEEE Journal of Selected Topics in Signal Processing","msr_affiliation":"","msr_published_date":"2012-12-01","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"959-970","msr_chapter":"","msr_isbn":"","msr_journal":"IEEE Journal of Selected Topics in Signal Processing","msr_volume":"6","msr_number":"8","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":"205754","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","title":"williams2012jstsp-2col.pdf","viewUrl":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-content\/uploads\/2016\/02\/williams2012jstsp-2col.pdf","id":205754,"label_id":0}],"msr_related_uploader":"","msr_citation_count":0,"msr_citation_count_updated":"","msr_s2_paper_id":"","msr_influential_citations":0,"msr_reference_count":0,"msr_arxiv_id":"","msr_s2_author_ids":[],"msr_s2_open_access":false,"msr_s2_pdf_url":null,"msr_attachments":[{"id":205754,"url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-content\/uploads\/2016\/02\/williams2012jstsp-2col.pdf"}],"msr-author-ordering":[{"type":"user_nicename","value":"jawillia","user_id":32190,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=jawillia"}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[],"msr_project":[171313],"publication":[],"video":[],"msr-tool":[],"msr_publication_type":"article","related_content":{"projects":[{"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:\/\/cm-edgetun.pages.dev\/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:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/171313"}]}}]},"_links":{"self":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/164154","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":1,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/164154\/revisions"}],"predecessor-version":[{"id":522737,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/164154\/revisions\/522737"}],"wp:attachment":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/media?parent=164154"}],"wp:term":[{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=164154"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=164154"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=164154"},{"taxonomy":"msr-publisher","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publisher?post=164154"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=164154"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=164154"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=164154"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=164154"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=164154"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=164154"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=164154"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=164154"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}