{"id":790874,"date":"2021-10-31T04:21:18","date_gmt":"2021-10-31T11:21:18","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-project&#038;p=790874"},"modified":"2024-09-10T08:56:32","modified_gmt":"2024-09-10T15:56:32","slug":"meeting-intelligence-task-rephrasing","status":"publish","type":"msr-project","link":"https:\/\/www.microsoft.com\/en-us\/research\/project\/meeting-intelligence-task-rephrasing\/","title":{"rendered":"Meeting Intelligence: Task Rephrasing"},"content":{"rendered":"<section class=\"mb-3 moray-highlight\">\n\t<div class=\"card-img-overlay mx-lg-0\">\n\t\t<div class=\"card-background  has-background- card-background--full-bleed\">\n\t\t\t<img loading=\"lazy\" decoding=\"async\" width=\"2560\" height=\"1441\" src=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2021\/08\/1400x788_Parallel_chat_No_logo_still-6109a566afcc8-scaled.jpg\" class=\"attachment-full size-full\" alt=\"Woman at a desk using a Surface laptop to make a Microsoft Teams video call with one man smiling and wearing a headset. Business Voice conference call\/meeting device is in the background.\" style=\"\" srcset=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2021\/08\/1400x788_Parallel_chat_No_logo_still-6109a566afcc8-scaled.jpg 2560w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2021\/08\/1400x788_Parallel_chat_No_logo_still-6109a566afcc8-300x169.jpg 300w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2021\/08\/1400x788_Parallel_chat_No_logo_still-6109a566afcc8-1024x577.jpg 1024w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2021\/08\/1400x788_Parallel_chat_No_logo_still-6109a566afcc8-768x432.jpg 768w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2021\/08\/1400x788_Parallel_chat_No_logo_still-6109a566afcc8-1536x865.jpg 1536w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2021\/08\/1400x788_Parallel_chat_No_logo_still-6109a566afcc8-2048x1153.jpg 2048w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2021\/08\/1400x788_Parallel_chat_No_logo_still-6109a566afcc8-1066x600.jpg 1066w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2021\/08\/1400x788_Parallel_chat_No_logo_still-6109a566afcc8-655x368.jpg 655w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2021\/08\/1400x788_Parallel_chat_No_logo_still-6109a566afcc8-343x193.jpg 343w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2021\/08\/1400x788_Parallel_chat_No_logo_still-6109a566afcc8-240x135.jpg 240w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2021\/08\/1400x788_Parallel_chat_No_logo_still-6109a566afcc8-640x360.jpg 640w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2021\/08\/1400x788_Parallel_chat_No_logo_still-6109a566afcc8-960x540.jpg 960w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2021\/08\/1400x788_Parallel_chat_No_logo_still-6109a566afcc8-1280x720.jpg 1280w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2021\/08\/1400x788_Parallel_chat_No_logo_still-6109a566afcc8-1920x1080.jpg 1920w\" sizes=\"(max-width: 2560px) 100vw, 2560px\" \/>\t\t<\/div>\n\t\t<!-- Foreground -->\n\t\t<div class=\"card-foreground d-flex mt-md-n5 my-lg-5 px-g px-lg-0\">\n\t\t\t<!-- Container -->\n\t\t\t<div class=\"container d-flex mt-md-n5 my-lg-5 align-self-center\">\n\t\t\t\t<!-- Card wrapper -->\n\t\t\t\t<div class=\"w-100 w-lg-col-5\">\n\t\t\t\t\t<!-- Card -->\n\t\t\t\t\t<div class=\"card material-md-card py-5 px-md-5\">\n\t\t\t\t\t\t<div class=\"card-body \">\n\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\n\n<h1 class=\"wp-block-heading\" id=\"meeting-intelligence-task-rephrasing\">Meeting Intelligence: Task Rephrasing<\/h1>\n\n\n\n<p>Exploratory project to &#8216;decontextualize&#8217; tasks and to-do items identified in meeting transcriptions, and rewrite each of them in a single sentence to appear in a separate to-do list. We build upon pretrained seq2seq transformer models, and modern techniques such as multitask learning, and touch upon unresolved issues such as automated metrics to evaluate NLG models.<\/p>\n\n\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t<\/div>\n\t\t<\/div>\n\t<\/div>\n<\/section>\n\n\n\n\n\n<p>In our teem, we build machine learning technology to detect tasks in emails, and explore the usage of this technology for the detection of tasks in meeting transcripts. In this exploratory project, we develop deep models for the <em>decontextualization<\/em> of tasks: given a task detected in the transcript, we identify its relevant context, and rephrase (rewrite) the task and its context into a coherent and self-contained sentence. This sentence may then appear as part of a separate to-do list.<\/p>\n\n\n","protected":false},"excerpt":{"rendered":"<p>Exploratory project to &#8216;decontextualize&#8217; tasks and to-do items identified in meeting transcriptions, and rewrite each of them in a single sentence to appear in a separate to-do list. We build upon pretrained seq2seq transformer models, and modern techniques such as multitask learning, and touch upon unresolved issues such as automated metrics to evaluate NLG models. [&hellip;]<\/p>\n","protected":false},"featured_media":764419,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","footnotes":""},"research-area":[13556,13545],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-790874","msr-project","type-msr-project","status-publish","has-post-thumbnail","hentry","msr-research-area-artificial-intelligence","msr-research-area-human-language-technologies","msr-locale-en_us","msr-archive-status-active"],"msr_project_start":"","related-publications":[790886],"related-downloads":[],"related-videos":[],"related-groups":[],"related-events":[],"related-opportunities":[],"related-posts":[],"related-articles":[],"tab-content":[],"slides":[],"related-researchers":[{"type":"user_nicename","display_name":"Amir Kantor","user_id":40153,"people_section":"Section name 0","alias":"amkantor"},{"type":"guest","display_name":"Atalya Waissman","user_id":810337,"people_section":"Section name 0","alias":""}],"msr_research_lab":[],"msr_impact_theme":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/790874"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-project"}],"version-history":[{"count":22,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/790874\/revisions"}],"predecessor-version":[{"id":1083882,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/790874\/revisions\/1083882"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/764419"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=790874"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=790874"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=790874"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=790874"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=790874"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}