{"id":663420,"date":"2020-06-18T23:02:38","date_gmt":"2020-06-19T06:02:38","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-project&p=663420"},"modified":"2020-10-02T19:48:58","modified_gmt":"2020-10-03T02:48:58","slug":"universal-question-answering-in-100-languages","status":"publish","type":"msr-project","link":"https:\/\/www.microsoft.com\/en-us\/research\/project\/universal-question-answering-in-100-languages\/","title":{"rendered":"Universal Question Answering in 100+ Languages"},"content":{"rendered":"
Question and Answering (QnA)<\/strong> aims to automatically answer natural language questions posed by human.<\/p>\n Motivated by the goal of providing Universal QnA experience to all Bing users,\u00a0 we built an universal QnA ranking pipeline from scratch based on a dozens of cross lingual technologies.<\/p>\n With only training data in English language, we manage to ship the QnA feature to 100+ languages and 200+ markets\/regions<\/strong> in very short term.<\/p>\n <\/p>\n <\/p>\n Arabic:<\/p>\n <\/p>\n Norwegian:<\/p>\n <\/p>\n Dutch:<\/p>\n <\/p>\n Russia:<\/p>\n <\/p>\n <\/p>\n Telugu:<\/p>\n <\/p>\n Frisian:<\/p>\n <\/p>\n <\/p>\n","protected":false},"excerpt":{"rendered":" Provide universal Question Answering experiment to hundreds of millions of users in 100+ languages, 200+ markets\/ regions, using cuttting edge cross lingual deep learning technologies. <\/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":""},"research-area":[13556],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-663420","msr-project","type-msr-project","status-publish","hentry","msr-research-area-artificial-intelligence","msr-locale-en_us","msr-archive-status-active"],"msr_project_start":"2019-07-01","related-publications":[668403,668412,668421,657132,663873,668394],"related-downloads":[746317],"related-videos":[],"related-groups":[],"related-events":[],"related-opportunities":[],"related-posts":[],"related-articles":[],"tab-content":[],"slides":[],"related-researchers":[{"type":"user_nicename","display_name":"Ming Gong (YIMING)","user_id":39078,"people_section":"Section name 0","alias":"migon"},{"type":"user_nicename","display_name":"Linjun Shou (\u5bff\u6797\u94a7)","user_id":39060,"people_section":"Section name 0","alias":"lisho"}],"msr_research_lab":[],"msr_impact_theme":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/663420"}],"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":16,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/663420\/revisions"}],"predecessor-version":[{"id":695895,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/663420\/revisions\/695895"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=663420"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=663420"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=663420"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=663420"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=663420"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}Example Cases:<\/h4>\n