{"id":183108,"date":"2007-02-19T00:00:00","date_gmt":"2009-10-31T10:19:19","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/msr-research-item\/belief-updating-in-spoken-language-interfaces\/"},"modified":"2016-09-09T09:49:21","modified_gmt":"2016-09-09T16:49:21","slug":"belief-updating-in-spoken-language-interfaces","status":"publish","type":"msr-video","link":"https:\/\/www.microsoft.com\/en-us\/research\/video\/belief-updating-in-spoken-language-interfaces\/","title":{"rendered":"Belief Updating in Spoken Language Interfaces"},"content":{"rendered":"<div class=\"asset-content\">\n<p>Over the last decade, advances in natural language processing technologies have paved the way for the emergence of complex spoken language interfaces. A persistent and important problem in the development of these systems is their lack of robustness when confronted with understanding-errors. The problem stems mostly from the unreliability of current speech recognition technology, and is present across all domains and interaction types. My research addresses this problem by: (1) endowing spoken language interfaces with better error awareness, (2) constructing and evaluating a rich repertoire of error recovery strategies, and (3) developing data-driven, adaptive approaches for making error handling decisions.<\/p>\n<p>In this talk, I focus on the first of these problems: error awareness.<br \/>\nTraditionally, spoken dialog systems rely on recognition confidence scores and simple heuristics to guard against potential misunderstandings. While confidence scores can provide an initial reliability assessment, ideally a system should leverage information from subsequent user turns in the conversation to continuously update and improve the accuracy of its beliefs.<\/p>\n<p>I describe a scalable data-driven solution for this belief updating problem. The proposed approach relies on a compressed concept-level representation of beliefs and casts the belief updating problem as a multinomial regression task. Experimental results indicate that the constructed belief updating models significantly outperform typical heuristic rules used in current systems. Furthermore, a user study with a deployed mixed-initiative spoken dialog system shows that the proposed approach leads to large improvements in both the effectiveness and the efficiency of the interaction across a wide range of recognition error rates.<\/p>\n<\/div>\n<p><!-- .asset-content --><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Over the last decade, advances in natural language processing technologies have paved the way for the emergence of complex spoken language interfaces. A persistent and important problem in the development of these systems is their lack of robustness when confronted with understanding-errors. The problem stems mostly from the unreliability of current speech recognition technology, and [&hellip;]<\/p>\n","protected":false},"featured_media":194901,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"research-area":[],"msr-video-type":[],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-183108","msr-video","type-msr-video","status-publish","has-post-thumbnail","hentry","msr-locale-en_us"],"msr_download_urls":"","msr_external_url":"https:\/\/youtu.be\/gVbDjXlxMa4","msr_secondary_video_url":"","msr_video_file":"","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/183108"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-video"}],"version-history":[{"count":0,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/183108\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/194901"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=183108"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=183108"},{"taxonomy":"msr-video-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video-type?post=183108"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=183108"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=183108"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=183108"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}