{"629435":{"#nid":"629435","#data":{"type":"event","title":"IC Guest Seminar with Alan Ritter, Ohio State University","body":[{"value":"\u003Cp\u003EThe School of Interactive Computing is hosting a guest seminar from Alan Ritter, an assistant professor in Computer Science and Engineering at Ohio State University.\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ETitle:\u003C\/strong\u003E\u003Cbr \/\u003E\r\nWhat\u0026rsquo;s so Hard About Natural Language Understanding?\u003Cbr \/\u003E\r\n\u003Cbr \/\u003E\r\n\u003Cstrong\u003EAbstract:\u003C\/strong\u003E\u003Cbr \/\u003E\r\nIn recent years, advances in speech recognition and machine translation (MT) have led to wide adoption, for\u0026nbsp;example, by helping people issue voice commands to their phone and talk with people who do not speak the\u0026nbsp;same language. These advances are possible due to the use of neural network methods on large, high-quality\u0026nbsp;datasets. However, computers still struggle to understand the meaning of language. In this talk, I will present two\u0026nbsp;efforts to scale up natural language understanding, drawing inspiration from recent successes in speech and MT.\u0026nbsp;\u0026nbsp;First, I will describe an effort to extract structured knowledge from text, without relying on human labels. \u0026nbsp;Our\u0026nbsp;approach combines the benefits of structured learning and neural networks, accurately predicting latent relation\u0026nbsp;mentions given only indirect supervision from a knowledge base. \u0026nbsp;In extensive experiments, we demonstrate that\u0026nbsp;the combination of structured inference, missing data modeling, and end-to-end learned representations leads to\u0026nbsp;state-of-the-art results on a minimally supervised relation extraction task. \u0026nbsp;In the second part of the talk, I will\u0026nbsp;discuss conversational agents that are learned from scratch in a purely data-driven way. \u0026nbsp;To address the challenge\u0026nbsp;of dull responses, which are common in neural dialogue, I will present several strategies that maximize the long-term success of a conversation.\u003Cbr \/\u003E\r\n\u003Cbr \/\u003E\r\n\u003Cstrong\u003EBio:\u003C\/strong\u003E\u003Cbr \/\u003E\r\nAlan Ritter is an assistant professor in Computer Science and Engineering at Ohio State University. His research\u0026nbsp;interests include natural language processing, information extraction, and machine learning. He completed his\u0026nbsp;Ph.D. at the University of Washington and was a postdoctoral fellow in the Machine Learning Department at\u0026nbsp;Carnegie Mellon. \u0026nbsp;His research aims to solve challenging technical problems that can help machines learn to read\u0026nbsp;vast quantities of text with minimal supervision. \u0026nbsp;In a recent project, \u003Ca href=\u0022https:\/\/www.wired.com\/story\/machine-learning-tweets-critical-security-flaws\/\u0022\u003Ecovered by WIRED\u003C\/a\u003E, his group built a system that reads\u0026nbsp;millions of tweets for mentions of new software vulnerabilities. \u0026nbsp;He is the recipient of an NSF CAREER award and\u0026nbsp;an Amazon Research Award.\u003C\/p\u003E\r\n","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"The School of Interactive Computing is hosting a guest seminar from Alan Ritter, an assistant professor in Computer Science and Engineering at Ohio State University. "}],"uid":"34773","created_gmt":"2019-11-27 14:44:53","changed_gmt":"2019-11-27 14:45:29","author":"ablinder6","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2019-12-02T14:00:00-05:00","event_time_end":"2019-12-02T15:00:00-05:00","event_time_end_last":"2019-12-02T15:00:00-05:00","gmt_time_start":"2019-12-02 19:00:00","gmt_time_end":"2019-12-02 20:00:00","gmt_time_end_last":"2019-12-02 20:00:00","rrule":null,"timezone":"America\/New_York"},"extras":[],"hg_media":{"629434":{"id":"629434","type":"image","title":"Alan Ritter","body":null,"created":"1574865629","gmt_created":"2019-11-27 14:40:29","changed":"1574865629","gmt_changed":"2019-11-27 14:40:29","alt":"Alan Ritter","file":{"fid":"239702","name":"Unknown-1.png","image_path":"\/sites\/default\/files\/images\/Unknown-1_1.png","image_full_path":"http:\/\/www.tlwarc.hg.gatech.edu\/\/sites\/default\/files\/images\/Unknown-1_1.png","mime":"image\/png","size":109095,"path_740":"http:\/\/www.tlwarc.hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/images\/Unknown-1_1.png?itok=lP-2YIDu"}}},"media_ids":["629434"],"groups":[{"id":"47223","name":"College of Computing"},{"id":"1299","name":"GVU Center"},{"id":"576481","name":"ML@GT"},{"id":"50876","name":"School of Interactive Computing"}],"categories":[],"keywords":[],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1795","name":"Seminar\/Lecture\/Colloquium"}],"invited_audience":[{"id":"78761","name":"Faculty\/Staff"},{"id":"177814","name":"Postdoc"},{"id":"78771","name":"Public"},{"id":"174045","name":"Graduate students"},{"id":"78751","name":"Undergraduate students"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003EDavid Mitchell\u003C\/p\u003E\r\n\r\n\u003Cp\u003ECommunications Officer II\u003C\/p\u003E\r\n\r\n\u003Cp\u003Edavid.mitchell@cc.gatech.edu\u003C\/p\u003E\r\n","format":"limited_html"}],"email":[],"slides":[],"orientation":[],"userdata":""}}}