{"id":769,"date":"2018-08-13T10:35:58","date_gmt":"2018-08-13T10:35:58","guid":{"rendered":"http:\/\/edinburghnlp.inf.ed.ac.uk\/?post_type=tribe_events&#038;p=769"},"modified":"2018-08-13T10:35:58","modified_gmt":"2018-08-13T10:35:58","slug":"shashi-narayan","status":"publish","type":"tribe_events","link":"https:\/\/edinburghnlp.inf.ed.ac.uk\/index.php\/event\/shashi-narayan\/","title":{"rendered":"Shashi Narayan"},"content":{"rendered":"<p>Title: Topic-Aware Convolutional Neural Networks for Extreme Summarization<\/p>\n<p>Abstract: we introduce extreme summarization, a new single-document summarization task which does not favor extractive strategies and calls for an abstractive modeling approach. The idea is to create a short, one-sentence news summary answering the question: &#8220;What is the article about?&#8221;. We collect a real-world, large-scale dataset for this task by harvesting online articles from the British Broadcasting Corporation (BBC). We propose a novel abstractive model which is conditioned on the article?s topics and based entirely on convolutional neural networks. We demonstrate experimentally that this architecture captures long-range dependencies in a document and recognizes pertinent content, outperforming an oracle extractive system and state-of-the-art abstractive approaches when evaluated automatically and by humans.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Title: Topic-Aware Convolutional Neural Networks for Extreme Summarization Abstract: we introduce extreme summarization, a new single-document summarization task which does not favor extractive strategies and calls for an abstractive modeling&hellip;<\/p>\n","protected":false},"author":4,"featured_media":0,"template":"","meta":{"_tribe_events_status":"","_tribe_events_status_reason":"","footnotes":""},"tags":[],"tribe_events_cat":[],"class_list":["post-769","tribe_events","type-tribe_events","status-publish","hentry","description-off"],"_links":{"self":[{"href":"https:\/\/edinburghnlp.inf.ed.ac.uk\/index.php\/wp-json\/wp\/v2\/tribe_events\/769","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/edinburghnlp.inf.ed.ac.uk\/index.php\/wp-json\/wp\/v2\/tribe_events"}],"about":[{"href":"https:\/\/edinburghnlp.inf.ed.ac.uk\/index.php\/wp-json\/wp\/v2\/types\/tribe_events"}],"author":[{"embeddable":true,"href":"https:\/\/edinburghnlp.inf.ed.ac.uk\/index.php\/wp-json\/wp\/v2\/users\/4"}],"version-history":[{"count":1,"href":"https:\/\/edinburghnlp.inf.ed.ac.uk\/index.php\/wp-json\/wp\/v2\/tribe_events\/769\/revisions"}],"predecessor-version":[{"id":770,"href":"https:\/\/edinburghnlp.inf.ed.ac.uk\/index.php\/wp-json\/wp\/v2\/tribe_events\/769\/revisions\/770"}],"wp:attachment":[{"href":"https:\/\/edinburghnlp.inf.ed.ac.uk\/index.php\/wp-json\/wp\/v2\/media?parent=769"}],"wp:term":[{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/edinburghnlp.inf.ed.ac.uk\/index.php\/wp-json\/wp\/v2\/tags?post=769"},{"taxonomy":"tribe_events_cat","embeddable":true,"href":"https:\/\/edinburghnlp.inf.ed.ac.uk\/index.php\/wp-json\/wp\/v2\/tribe_events_cat?post=769"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}