{"id":12014,"date":"2019-04-01T06:00:44","date_gmt":"2019-04-01T10:00:44","guid":{"rendered":"http:\/\/whamit.mit.edu\/?p=12014"},"modified":"2019-03-31T20:49:17","modified_gmt":"2019-04-01T00:49:17","slug":"comp-lang-4-4-candace-ross-mit-csail","status":"publish","type":"post","link":"https:\/\/ling-phil.mit.edu\/whamit\/2019\/04\/01\/comp-lang-4-4-candace-ross-mit-csail\/","title":{"rendered":"Comp-Lang 4\/4 - Candace Ross (MIT CSAIL)"},"content":{"rendered":"\n<p class=\"wp-block-paragraph\"><strong>Speaker<\/strong>:&nbsp;&nbsp;<a href=\"https:\/\/cbmm.mit.edu\/about\/people\/ross\">Candace Ross<\/a> (MIT CSAIL)<br><strong>Title<\/strong>:&nbsp;Grounding Language Acquisition by Training Semantic Parsers using Captioned Videos<br><strong>Time<\/strong>:&nbsp;Thursday, 4\/4, 5-6pm<br><strong>Location<\/strong>:&nbsp;46-5165<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Abstract:<\/strong><br>We develop a semantic  parser that is trained in a grounded setting using pairs of videos  captioned with sentences. This setting is both data-efficient, requiring  little annotation, and similar to the experience  of children where they observe their environment and listen to  speakers. The semantic parser recovers the meaning of English sentences  despite not having access to any annotated sentences. It does so despite  the ambiguity inherent in vision where a sentence  may refer to any combination of objects, object properties, relations  or actions taken by any agent in a video. For this task, we collected a  new dataset for grounded language acquisition. Learning a grounded  semantic parser \u0097 turning sentences into logical  forms using captioned videos \u0097 can significantly expand the range of  data that parsers can be trained on, lower the effort of training a  semantic parser, and ultimately lead to a better understanding of child  language acquisition.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Speaker:&nbsp;&nbsp;Candace Ross (MIT CSAIL)Title:&nbsp;Grounding Language Acquisition by Training Semantic Parsers using Captioned VideosTime:&nbsp;Thursday, 4\/4, 5-6pmLocation:&nbsp;46-5165 Abstract:We develop a semantic parser that is trained in a grounded setting using pairs of videos captioned with sentences. This setting is both data-efficient, requiring little annotation, and similar to the experience of children where they observe their environment and [&hellip;]<\/p>\n","protected":false},"author":21,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-12014","post","type-post","status-publish","format-standard","hentry","category-announcements"],"_links":{"self":[{"href":"https:\/\/ling-phil.mit.edu\/whamit\/wp-json\/wp\/v2\/posts\/12014","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/ling-phil.mit.edu\/whamit\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/ling-phil.mit.edu\/whamit\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/ling-phil.mit.edu\/whamit\/wp-json\/wp\/v2\/users\/21"}],"replies":[{"embeddable":true,"href":"https:\/\/ling-phil.mit.edu\/whamit\/wp-json\/wp\/v2\/comments?post=12014"}],"version-history":[{"count":5,"href":"https:\/\/ling-phil.mit.edu\/whamit\/wp-json\/wp\/v2\/posts\/12014\/revisions"}],"predecessor-version":[{"id":12038,"href":"https:\/\/ling-phil.mit.edu\/whamit\/wp-json\/wp\/v2\/posts\/12014\/revisions\/12038"}],"wp:attachment":[{"href":"https:\/\/ling-phil.mit.edu\/whamit\/wp-json\/wp\/v2\/media?parent=12014"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/ling-phil.mit.edu\/whamit\/wp-json\/wp\/v2\/categories?post=12014"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/ling-phil.mit.edu\/whamit\/wp-json\/wp\/v2\/tags?post=12014"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}