{"id":12763,"date":"2019-10-07T06:02:00","date_gmt":"2019-10-07T10:02:00","guid":{"rendered":"http:\/\/whamit.mit.edu\/?p=12763"},"modified":"2019-10-07T06:02:00","modified_gmt":"2019-10-07T10:02:00","slug":"linglunch-10-10-ethan-wilcox-harvard","status":"publish","type":"post","link":"https:\/\/ling-phil.mit.edu\/whamit\/2019\/10\/07\/linglunch-10-10-ethan-wilcox-harvard\/","title":{"rendered":"LingLunch 10\/10 - Ethan Wilcox (Harvard)"},"content":{"rendered":"<p><strong>Speaker: <\/strong> Ethan Wilcox (Harvard)<br clear='none'\/><strong>Title: <\/strong>Neural Network Models and the Argument from the Poverty of the Stimulus: The Case of Filler\u0097Gap Dependencies<br clear='none'\/><strong>Time: <\/strong>Thursday, October 10th, 12:30pm - 1:50pm<br clear='none'\/><strong>Location: <\/strong>32-D461<\/p>\n<p><strong>Abstract: <\/strong>Recurrent Neural Networks (RNNs) are one type of neural model that has been able to achieve state-of-the-art scores on a variety of natural language tasks, including translation and language modeling (which is used in, for example, text prediction). In this talk I will assess how these models might way in to linguistic debates about the types of biases required to learn syntactic structures. By treating these models like subjects in a psycholinguistics experiment, I will demonstrate that they are able to learn the filler&#8212;gap dependency, and are even sensitive to the hierarchical constraints implicated in the dependency. Next, I turn to &#8220;island effects&#8221;, or structural configurations that block the filler&#8212;gap dependency, which have historically played a role in the Argument from the Poverty of the Stimulus. I demonstrate that RNNs are able to learn some of the &#8220;island&#8221; constraints and even recover some of their pre-island gap expectation. These experiments demonstrate that linear statistical models are able to learn some fine-grained syntactic rules, however their behavior remains un-humanlike in many cases.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Speaker: Ethan Wilcox (Harvard)Title: Neural Network Models and the Argument from the Poverty of the Stimulus: The Case of Filler\u0097Gap DependenciesTime: Thursday, October 10th, 12:30pm - 1:50pmLocation: 32-D461 Abstract: Recurrent Neural Networks (RNNs) are one type of neural model that has been able to achieve state-of-the-art scores on a variety of natural language tasks, including [&hellip;]<\/p>\n","protected":false},"author":26,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-12763","post","type-post","status-publish","format-standard","hentry","category-announcements"],"_links":{"self":[{"href":"https:\/\/ling-phil.mit.edu\/whamit\/wp-json\/wp\/v2\/posts\/12763","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\/26"}],"replies":[{"embeddable":true,"href":"https:\/\/ling-phil.mit.edu\/whamit\/wp-json\/wp\/v2\/comments?post=12763"}],"version-history":[{"count":1,"href":"https:\/\/ling-phil.mit.edu\/whamit\/wp-json\/wp\/v2\/posts\/12763\/revisions"}],"predecessor-version":[{"id":12825,"href":"https:\/\/ling-phil.mit.edu\/whamit\/wp-json\/wp\/v2\/posts\/12763\/revisions\/12825"}],"wp:attachment":[{"href":"https:\/\/ling-phil.mit.edu\/whamit\/wp-json\/wp\/v2\/media?parent=12763"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/ling-phil.mit.edu\/whamit\/wp-json\/wp\/v2\/categories?post=12763"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/ling-phil.mit.edu\/whamit\/wp-json\/wp\/v2\/tags?post=12763"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}