{"id":21787,"date":"2018-01-16T04:55:53","date_gmt":"2018-01-16T04:55:53","guid":{"rendered":"http:\/\/www.kurzweilai.net\/?p=308062"},"modified":"2018-01-16T04:55:53","modified_gmt":"2018-01-16T04:55:53","slug":"deep-neural-network-models-score-higher-than-humans-in-reading-and-comprehension-test","status":"publish","type":"post","link":"https:\/\/hoo.central12.com\/fugic\/2018\/01\/16\/deep-neural-network-models-score-higher-than-humans-in-reading-and-comprehension-test\/","title":{"rendered":"Deep neural network models score higher than humans in reading and comprehension test"},"content":{"rendered":"<div id=\"attachment_308073\" class=\"wp-caption aligncenter\" style=\"width: 560px;  border: 1px solid #dddddd; background-color: #f3f3f3; padding-top: 4px; margin: 10px; text-align:center; display: block; margin-right: auto; margin-left: auto;\"><img class=\" wp-image-308073\" title=\"Alibaba Group\" src=\"http:\/\/www.kurzweilai.net\/images\/Alibaba-Group.png\" alt=\"\" width=\"550\" height=\"232\" \/><p style=' padding: 0 4px 5px; margin: 0;'  class=\"wp-caption-text\">(credit: Alibaba Group)<\/p><\/div>\n<p>Microsoft has developed a deep neural network that scored higher than humans on exact scores in a Stanford University reading and comprehension test <a href=\"https:\/\/rajpurkar.github.io\/SQuAD-explorer\/\" ><strong>S<\/strong>tanford <strong>Qu<\/strong>estion <strong>A<\/strong>nswering <strong>D<\/strong>ataset <\/a>(SQuAD).<\/p>\n<p>Microsoft achieved 82.650 on Jan. 3; <a title=\"Company Overview\" href=\"https:\/\/www.bloomberg.com\/quote\/BABA:US\" rel=\"nofollow noopener\">Alibaba Group Holding Ltd.<\/a> came in at second place at 82.440 on Jan. 5. The best human score so far is 82.304.<\/p>\n<p>&#8220;SQuAD is a new reading comprehension dataset, consisting of questions posed by crowdworkers on a set of Wikipedia articles, where the answer to every question is a segment of text, or <em>span<\/em>, from the corresponding reading passage,&#8221; according to the Stanford NLP Group. &#8220;With 100,000+ question-answer pairs on 500+ articles, SQuAD is significantly larger than previous reading comprehension datasets.&#8221;<\/p>\n<p>&#8220;The Chinese e-commerce titan has joined the likes of\u00a0<a title=\"Company Overview\" href=\"https:\/\/www.bloomberg.com\/quote\/700:HK\" rel=\"nofollow noopener\">Tencent Holdings Ltd.<\/a>\u00a0and\u00a0<a title=\"Company Overview\" href=\"https:\/\/www.bloomberg.com\/quote\/BIDU:US\" rel=\"nofollow noopener\">Baidu Inc.<\/a>\u00a0in a race to develop AI that can enrich social media feeds, target ads and services or even aid in autonomous driving, Bloomberg notes. &#8220;Beijing has endorsed the technology in a national-level plan that calls for the country to become the industry leader 2030.&#8221;<\/p>\n<p data-tout-type=\"story\"><a title=\"Click for full story\" href=\"https:\/\/www.bloomberg.com\/news\/articles\/2017-08-14\/china-s-plan-for-world-domination-in-ai-isn-t-so-crazy-after-all\" >Read more: China\u2019s Plan for World Domination in AI (Bloomberg)<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Microsoft has developed a deep neural network that scored higher than humans on exact scores in a Stanford University reading and comprehension test Stanford Question Answering Dataset (SQuAD). Microsoft achieved 82.650 on Jan. 3; Alibaba Group Holding Ltd. came in at second place at 82.440 on Jan. 5. The best human score so far is [&#8230;]<\/p>\n","protected":false},"author":13,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[46,43],"tags":[],"class_list":["post-21787","post","type-post","status-publish","format-standard","hentry","category-airobotics","category-news"],"_links":{"self":[{"href":"https:\/\/hoo.central12.com\/fugic\/wp-json\/wp\/v2\/posts\/21787"}],"collection":[{"href":"https:\/\/hoo.central12.com\/fugic\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/hoo.central12.com\/fugic\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/hoo.central12.com\/fugic\/wp-json\/wp\/v2\/users\/13"}],"replies":[{"embeddable":true,"href":"https:\/\/hoo.central12.com\/fugic\/wp-json\/wp\/v2\/comments?post=21787"}],"version-history":[{"count":1,"href":"https:\/\/hoo.central12.com\/fugic\/wp-json\/wp\/v2\/posts\/21787\/revisions"}],"predecessor-version":[{"id":21789,"href":"https:\/\/hoo.central12.com\/fugic\/wp-json\/wp\/v2\/posts\/21787\/revisions\/21789"}],"wp:attachment":[{"href":"https:\/\/hoo.central12.com\/fugic\/wp-json\/wp\/v2\/media?parent=21787"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hoo.central12.com\/fugic\/wp-json\/wp\/v2\/categories?post=21787"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hoo.central12.com\/fugic\/wp-json\/wp\/v2\/tags?post=21787"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}