{"id":166395,"date":"2014-04-01T00:00:00","date_gmt":"2014-04-01T00:00:00","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/msr-research-item\/zero-shot-learning-and-clustering-for-semantic-utterance-classification\/"},"modified":"2018-10-16T20:16:22","modified_gmt":"2018-10-17T03:16:22","slug":"zero-shot-learning-and-clustering-for-semantic-utterance-classification","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/zero-shot-learning-and-clustering-for-semantic-utterance-classification\/","title":{"rendered":"Zero-Shot Learning and Clustering for Semantic Utterance Classification"},"content":{"rendered":"<div class=\"asset-content\">\n<p>We propose a novel zero-shot learning method for semantic utterance classification (SUC). It learns a classifier f : X -> Y for problems where none of the semantic categories Y are present in the training set. The framework uncovers the link between categories and utterances through a semantic space. We show that this semantic space can be learned by deep neural networks trained on large amounts of search engine query log data. What\u2019s more, we propose a novel method that can learn discriminative semantic features without supervision. It uses the zero-shot learning framework to guide the learning of the semantic features. We demonstrate the effectiveness of the zero-shot semantic learning algorithm on the SUC dataset collected by [1]. Furthermore, we achieve state-of-the-art results by combining the semantic features with a supervised method.<\/p>\n<\/div>\n<p><!-- .asset-content --><\/p>\n","protected":false},"excerpt":{"rendered":"<p>We propose a novel zero-shot learning method for semantic utterance classification (SUC). It learns a classifier f : X -> Y for problems where none of the semantic categories Y are present in the training set. The framework uncovers the link between categories and utterances through a semantic space. We show that this semantic space [&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":[13545,13554],"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-166395","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-human-language-technologies","msr-research-area-human-computer-interaction","msr-locale-en_us"],"msr_publishername":"International Conference on Learning Representations (ICLR)","msr_edition":"","msr_affiliation":"","msr_published_date":"2014-04-01","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":"217756","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","title":"1401.0509v2.pdf","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2014\/04\/1401.0509v2.pdf","id":217756,"label_id":0}],"msr_related_uploader":"","msr_attachments":[{"id":217756,"url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2014\/04\/1401.0509v2.pdf"}],"msr-author-ordering":[{"type":"user_nicename","value":"gokhant","user_id":31896,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=gokhant"},{"type":"user_nicename","value":"dilekha","user_id":31630,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=dilekha"},{"type":"user_nicename","value":"lheck","user_id":32659,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=lheck"}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[],"msr_project":[171393,171150],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","related_content":{"projects":[{"ID":171393,"post_title":"Knowledge Graphs and Linked Big Data Resources for Conversational Understanding","post_name":"knowledge-graphs-and-linked-big-data-resources-for-conversational-understanding","post_type":"msr-project","post_date":"2014-08-13 20:10:32","post_modified":"2017-06-19 11:05:46","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/knowledge-graphs-and-linked-big-data-resources-for-conversational-understanding\/","post_excerpt":"Interspeech 2014 Tutorial Web Page State-of-the-art statistical spoken language processing typically requires significant manual effort to construct domain-specific schemas (ontologies) as well as manual effort to annotate training data against these schemas. At the same time, a recent surge of activity and progress on semantic web-related concepts from the large search-engine companies represents a potential alternative to the manually intensive design of spoken language processing systems. Standards such as schema.org have been established for schemas&hellip;","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/171393"}]}},{"ID":171150,"post_title":"Spoken Language Understanding","post_name":"spoken-language-understanding","post_type":"msr-project","post_date":"2013-05-01 11:46:32","post_modified":"2019-08-19 14:48:51","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/spoken-language-understanding\/","post_excerpt":"Spoken language understanding (SLU) is an emerging field in between the areas of speech processing and natural language processing. The term spoken language understanding has largely been coined for targeted understanding of human speech directed at machines. This project covers our research on SLU tasks such as domain detection, intent determination, and slot filling, using data-driven methods. Projects Deeper Understanding: Moving\u00a0beyond shallow targeted understanding towards building domain independent SLU models. Scaling SLU: Quickly bootstrapping SLU&hellip;","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/171150"}]}}]},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/166395","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":1,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/166395\/revisions"}],"predecessor-version":[{"id":525592,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/166395\/revisions\/525592"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=166395"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=166395"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=166395"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=166395"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=166395"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=166395"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=166395"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=166395"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=166395"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=166395"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=166395"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=166395"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=166395"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=166395"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=166395"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=166395"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}