{"id":166870,"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\/neural-network-models-for-lexical-addressee-detection\/"},"modified":"2018-10-16T21:07:33","modified_gmt":"2018-10-17T04:07:33","slug":"neural-network-models-for-lexical-addressee-detection","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/neural-network-models-for-lexical-addressee-detection\/","title":{"rendered":"Neural Network Models for Lexical Addressee Detection"},"content":{"rendered":"<div class=\"asset-content\">\n<p>Addressee detection for dialog systems aims to detect which utterances are directed at the system, as opposed to someone else. An important means for classification is the lexical content of the utterance, and N-gram models have been shown to be effective for this task. In this paper we investigate whether neural networks can enhance lexical addressee detection, using data from a human-human-computer dialog system. Even though we find no improvement from simply replacing the standard Ngram LM with a neural-network LM as class likelihood estimators, improved classification accuracy can be obtained from a modified neural net model that learns distributed word representations in a first training phase, and is trained on the utterance classification task in a second phase. We obtain additional gains by combining the class likelihood estimation and classification training criteria in the second phase, and by combining multiple model architectures at the score level. Overall, we achieve over 2% absolute reduction in equal error rate over the N-gram model baseline of 27%.<\/p>\n<\/div>\n<p><!-- .asset-content --><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Addressee detection for dialog systems aims to detect which utterances are directed at the system, as opposed to someone else. An important means for classification is the lexical content of the utterance, and N-gram models have been shown to be effective for this task. In this paper we investigate whether neural networks can enhance lexical [&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":[13545],"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-166870","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-human-language-technologies","msr-locale-en_us"],"msr_publishername":"ISCA - International Speech Communication Association","msr_edition":"Proc. Interspeech","msr_affiliation":"","msr_published_date":"2014-09-01","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"Proc. Interspeech","msr_pages_string":"298-302","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":"204687","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","title":"NNLM_addressee.pdf","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/02\/NNLM_addressee.pdf","id":204687,"label_id":0}],"msr_related_uploader":"","msr_attachments":[{"id":204687,"url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/02\/NNLM_addressee.pdf"}],"msr-author-ordering":[{"type":"text","value":"Suman Ravuri","user_id":0,"rest_url":false},{"type":"user_nicename","value":"anstolck","user_id":31054,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=anstolck"}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[],"msr_project":[171313],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","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:\/\/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\/166870","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\/166870\/revisions"}],"predecessor-version":[{"id":533071,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/166870\/revisions\/533071"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=166870"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=166870"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=166870"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=166870"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=166870"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=166870"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=166870"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=166870"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=166870"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=166870"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=166870"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=166870"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=166870"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=166870"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=166870"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=166870"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}