{"id":592723,"date":"2019-07-09T08:41:21","date_gmt":"2019-07-09T15:41:21","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-project&#038;p=592723"},"modified":"2020-11-12T13:44:24","modified_gmt":"2020-11-12T21:44:24","slug":"machine-reading-comprehension","status":"publish","type":"msr-project","link":"https:\/\/www.microsoft.com\/en-us\/research\/project\/machine-reading-comprehension\/","title":{"rendered":"Machine Reading Comprehension"},"content":{"rendered":"<p>Machine Reading Comprehension (MRC), or the ability to read and understand unstructured text and then answer questions about it remains a challenging task for computers. MRC is a growing field of research due to its potential in various enterprise applications, as well as the availability of MRC benchmarking datasets (MSMARCO, SQuAD, NewsQA, etc.)<\/p>\n<p>At Microsoft Research Montreal, we are developing algorithms that can learn to answer questions about new documents with limited amount of training data, incorporate common sense, and leverage external knowledge about the world. Our primary goal is questioning-answering in the real world: we envision an experience where getting the answers you need to complex questions about your documents is simple, effective, and intuitive.<\/p>\n<p>We&#8217;ve created an interactive demo that showcases the question answering technology developed using MRC.<\/p>\n<div>\n\t<a\n\t\thref=\"https:\/\/aka.ms\/mrc-demo-canada\"\n\t\tclass=\"button cta-link\"\n\t\tdata-bi-type=\"button\"\n\t\tdata-bi-cN=\"Try the Welcome To Canada Demo\"\n\t\tdata-bi-tN=\"shortcodes\/msr-button\"\n\t\t>\n\t\tTry the Welcome To Canada Demo\t<\/a>\n\n\t<\/div>\n","protected":false},"excerpt":{"rendered":"<p>Machine Reading Comprehension (MRC) is a growing field of research, due to its potential in various enterprise applications, as well as the availability of MRC benchmarking datasets.<\/p>\n","protected":false},"featured_media":596791,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","footnotes":""},"research-area":[13556],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-592723","msr-project","type-msr-project","status-publish","has-post-thumbnail","hentry","msr-research-area-artificial-intelligence","msr-locale-en_us","msr-archive-status-active"],"msr_project_start":"2019-07-09","related-publications":[549276,558447,595504,546099,547374,558489,495110,549297,480471,466575,455568,445488,445494,455544,442251,445104,445113,445512,598555],"related-downloads":[],"related-videos":[],"related-groups":[],"related-events":[],"related-opportunities":[],"related-posts":[],"related-articles":[],"tab-content":[],"slides":[],"related-researchers":[{"type":"user_nicename","display_name":"Mahmoud Adada","user_id":37176,"people_section":"Section name 1","alias":"maadada"},{"type":"user_nicename","display_name":"Luiz Belussi","user_id":37080,"people_section":"Section name 1","alias":"lubeluss"},{"type":"user_nicename","display_name":"Rahul Mehrotra","user_id":37203,"people_section":"Section name 1","alias":"ramehrot"},{"type":"user_nicename","display_name":"Tatsuro Oya","user_id":37140,"people_section":"Section name 1","alias":"taoy"},{"type":"user_nicename","display_name":"Alessandro Sordoni","user_id":37230,"people_section":"Section name 1","alias":"alsordon"},{"type":"user_nicename","display_name":"Eric Yuan","user_id":37167,"people_section":"Section name 1","alias":"eryua"},{"type":"user_nicename","display_name":"Dennis Zhuang","user_id":37401,"people_section":"Section name 1","alias":"enzhuang"}],"msr_research_lab":[437514],"msr_impact_theme":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/592723"}],"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":8,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/592723\/revisions"}],"predecessor-version":[{"id":696574,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/592723\/revisions\/696574"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/596791"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=592723"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=592723"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=592723"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=592723"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=592723"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}