{"id":2466,"date":"2009-04-27T13:50:23","date_gmt":"2009-04-27T18:50:23","guid":{"rendered":"http:\/\/www.theoreti.ca\/?p=2466"},"modified":"2009-08-25T20:40:16","modified_gmt":"2009-08-26T01:40:16","slug":"ibm-watson-question-answering-for-jeopardy","status":"publish","type":"post","link":"https:\/\/theoreti.ca\/?p=2466","title":{"rendered":"IBM Watson: Question Answering for Jeopardy"},"content":{"rendered":"<p><a href='http:\/\/www.theoreti.ca\/wp-content\/uploads\/2009\/04\/single_jeopardy_game_board.jpg' title='Jeopardy Board'><img src='http:\/\/www.theoreti.ca\/wp-content\/uploads\/2009\/04\/single_jeopardy_game_board.jpg' alt='Jeopardy Board' align=\"left\" vspace=\"5\" hspace=\"5\"\/><\/a>From <a href=\"http:\/\/www.youtube.com\/user\/IBMLabs\">IBM Labs YouTube presence<\/a> news of a <a href=\"http:\/\/www.youtube.com\/watch?v=3e22ufcqfTs\">IBM &#8220;Watson&#8221; System to Challenge Humans at Jeopardy!<\/a> IBM&#8217;s <a href=\"http:\/\/www.research.ibm.com\/deepqa\/\">Watson<\/a> is a Question Answering system that IBM scientists hope &#8220;will be able to understand complex questions and answer with enough precision and speed to compete on Jeopardy!&#8221; (<a href=\"http:\/\/www-03.ibm.com\/press\/us\/en\/pressrelease\/27324.wss\">From the IBM press release<\/a>.)<\/p>\n<blockquote><p>Watson will be designed to deftly handle semantics &#8220;the meanings behind words&#8221; which will enable it to answer questions that require the identification of relevant and irrelevant content, the interpretation of ambiguous expression and puns, the decomposition of questions into sub-questions, and the logical synthesis of final answers. In addition, Watson will compute a statistical confidence in the responses it provides. Watson will be designed to do all of this in a matter of seconds, which will enable it to compete against humans, who have the ability to know what they know in less than a second. (From <a href=\"http:\/\/www-03.ibm.com\/press\/us\/en\/pressrelease\/27324.wss\">Addendum: About IBM&#8217;s Watson System<\/a>)<\/p><\/blockquote>\n<p>The language IBM uses around this project is that of a &#8220;Grand Challenge.&#8221; It is smart how they have taken a analytical problem and used Jeopardy to give a target for the research, both in terms of speed and the types of questioning handled. Jeopardy also gives them a dramatic venue to demonstrate their progress just as Deep Blue playing Kasparov did.<\/p>\n<p>The research is based on a <a href=\"http:\/\/www.research.ibm.com\/deepqa\/question_answering.shtml\">Open Architecture for Question Answering<\/a> (OAQA) that was jointly developed with Carnegie Mellon.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>From IBM Labs YouTube presence news of a IBM &#8220;Watson&#8221; System to Challenge Humans at Jeopardy! IBM&#8217;s Watson is a Question Answering system that IBM scientists hope &#8220;will be able to understand complex questions and answer with enough precision and speed to compete on Jeopardy!&#8221; (From the IBM press release.) Watson will be designed to &hellip; <a href=\"https:\/\/theoreti.ca\/?p=2466\" class=\"more-link\">Continue reading <span class=\"screen-reader-text\">IBM Watson: Question Answering for Jeopardy<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[16],"tags":[],"class_list":["post-2466","post","type-post","status-publish","format-standard","hentry","category-text-analysis"],"_links":{"self":[{"href":"https:\/\/theoreti.ca\/index.php?rest_route=\/wp\/v2\/posts\/2466","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/theoreti.ca\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/theoreti.ca\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/theoreti.ca\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/theoreti.ca\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=2466"}],"version-history":[{"count":1,"href":"https:\/\/theoreti.ca\/index.php?rest_route=\/wp\/v2\/posts\/2466\/revisions"}],"predecessor-version":[{"id":2614,"href":"https:\/\/theoreti.ca\/index.php?rest_route=\/wp\/v2\/posts\/2466\/revisions\/2614"}],"wp:attachment":[{"href":"https:\/\/theoreti.ca\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=2466"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/theoreti.ca\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=2466"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/theoreti.ca\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=2466"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}