Recently, resources and tasks were proposed to go beyond state tracking in dialogue systems. An example is the frame tracking task, which requires recording multiple frames, one for each user goal set during the dialogue. This allows a user, for instance, to compare items corresponding to different goals. This paper proposes a model which takes as input the list of frames created so far during the dialogue, the current user utterance as well as the dialogue acts, slot types, and slot values associated with this utterance. The model then outputs the frame being referenced by each triple of dialogue act, slot type, and slot value. We show that on the recently published Frames dataset, this model significantly outperforms a previously proposed rule-based baseline. In addition, we propose an extensive analysis of the frame tracking task by dividing it into sub-tasks and assessing their difficulty with respect to our model.<\/p>\n","protected":false},"excerpt":{"rendered":"
Recently, resources and tasks were proposed to go beyond state tracking in dialogue systems. An example is the frame tracking task, which requires recording multiple frames, one for each user goal set during the dialogue. This allows a user, for instance, to compare items corresponding to different goals. This paper proposes a model which takes […]<\/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":[13556,13545],"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-390467","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-research-area-human-language-technologies","msr-locale-en_us"],"msr_publishername":"Association for Computational Linguistics","msr_edition":"","msr_affiliation":"","msr_published_date":"2017-08-03","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"Proceedings of the 2nd Workshop on Representation Learning for NLP","msr_pages_string":"219-227","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":"","msr_publicationurl":"http:\/\/www.aclweb.org\/anthology\/W17-2626","msr_doi":"","msr_publication_uploader":[{"type":"url","title":"http:\/\/www.aclweb.org\/anthology\/W17-2626","viewUrl":false,"id":false,"label_id":0}],"msr_related_uploader":"","msr_attachments":[{"id":0,"url":"http:\/\/www.aclweb.org\/anthology\/W17-2626"}],"msr-author-ordering":[{"type":"edited_text","value":"Hannes Schulz","user_id":37188,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Hannes Schulz"},{"type":"text","value":"Jeremie Zumer","user_id":0,"rest_url":false},{"type":"edited_text","value":"Layla El Asri","user_id":37134,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Layla El Asri"},{"type":"user_nicename","value":"shsh","user_id":36557,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=shsh"}],"msr_impact_theme":[],"msr_research_lab":[437514],"msr_event":[],"msr_group":[],"msr_project":[487187],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","related_content":{"projects":[{"ID":487187,"post_title":"Frames Dataset","post_name":"frames-dataset","post_type":"msr-project","post_date":"2019-01-14 09:39:09","post_modified":"2023-03-30 12:23:16","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/frames-dataset\/","post_excerpt":"Motivation A generation of voice assistants such as Siri, Cortana, and Google Now have been popular spoken dialogue systems. More recently, we have seen a rise in text-based conversational agents (aka chatbots). Text is preferred to voice by many users for privacy reasons and in order to avoid bad speech recognition in noisy environments. These agents are also welcome as an alternative to downloading and installing applications. This makes a lot of sense when completing…","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/487187"}]}}]},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/390467","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\/390467\/revisions"}],"predecessor-version":[{"id":390470,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/390467\/revisions\/390470"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=390467"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=390467"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=390467"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=390467"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=390467"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=390467"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=390467"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=390467"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=390467"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=390467"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=390467"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=390467"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=390467"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=390467"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=390467"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=390467"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}