{"id":249131,"date":"2018-03-13T22:02:53","date_gmt":"2018-03-14T05:02:53","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-project&#038;p=249131"},"modified":"2018-03-16T00:06:52","modified_gmt":"2018-03-16T07:06:52","slug":"open-domain-question-answering","status":"publish","type":"msr-project","link":"https:\/\/www.microsoft.com\/en-us\/research\/project\/open-domain-question-answering\/","title":{"rendered":"Question Answering (QA)"},"content":{"rendered":"<p><strong>Question Answering (QA)<\/strong>\u00a0aims to automatically answer natural language questions posed by human. In MSRA QA team, we are working on QA from two\u00a0angles: Single-turn QA and Conversational QA.<\/p>\n<p><span style=\"color: #0000ff\">Single-turn QA<\/span>\u00a0takes a single question as input and provides its answer as output without considering any context. We are building state-of-the-art single-turn QA engines based on heterogeneous databases, including <span style=\"color: #ff0000\">Knowledge-based QA<\/span>, <span style=\"color: #ff0000\">Table\/List-based QA<\/span>, <span style=\"color: #ff0000\">Text-based QA<\/span>, <span style=\"color: #ff0000\">Community-based QA<\/span>, and <span style=\"color: #ff0000\">Visual QA<\/span>. Both Microsoft Bing and Xiaoice have used these technologies already.<\/p>\n<p><span style=\"color: #0000ff\">Conversational QA<\/span><span style=\"color: #0000ff\"><span style=\"color: #000000\">, on the other hand,\u00a0<\/span><\/span>considers not only current input question, but also previous conversation turns. New problems should be addressed in\u00a0such multi-turn scenario, such as Coreference Resolution, State Tracking, Proactive\u00a0Asking\/Confirming. Conversational QA is critical to intelligent personal assistants and chatbots,\u00a0such as Microsoft Cortana and Xiaoice.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Question Answering (QA)\u00a0aims to automatically answer natural language questions posed by human. In MSRA QA team, we are working on QA from two\u00a0angles: Single-turn QA and Conversational QA. Single-turn QA\u00a0takes a single question as input and provides its answer as output without considering any context. We are building state-of-the-art single-turn QA engines based on heterogeneous [&hellip;]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"research-area":[13556],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-249131","msr-project","type-msr-project","status-publish","hentry","msr-research-area-artificial-intelligence","msr-locale-en_us","msr-archive-status-active"],"msr_project_start":"","related-publications":[],"related-downloads":[],"related-videos":[],"related-groups":[],"related-events":[],"related-opportunities":[],"related-posts":[],"related-articles":[],"tab-content":[],"slides":[],"related-researchers":[{"type":"user_nicename","display_name":"Yaobo Liang","user_id":36036,"people_section":"Section name 1","alias":"yalia"},{"type":"user_nicename","display_name":"Lei Ji","user_id":32636,"people_section":"Section name 1","alias":"leiji"}],"msr_research_lab":[199560],"msr_impact_theme":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/249131"}],"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":11,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/249131\/revisions"}],"predecessor-version":[{"id":473409,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/249131\/revisions\/473409"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=249131"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=249131"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=249131"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=249131"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=249131"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}