{"392461":{"#nid":"392461","#data":{"type":"event","title":"Ph.D Proposal Defense by Yangfeng Ji","body":[{"value":"\u003Cp\u003EPh.D. Thesis Proposal Announcement\u003Cbr \/\u003E\u003Cbr \/\u003ETitle: \u003Cstrong\u003ESemantic Representation Learning for Discourse Processing\u003C\/strong\u003E\u003Cbr \/\u003E\u003Cbr \/\u003E\u003Cstrong\u003EYangfeng Ji\u003C\/strong\u003E\u003Cbr \/\u003EPh.D. Student\u003Cbr \/\u003ESchool of Interactive Computing\u003Cbr \/\u003ECollege of Computing\u003Cbr \/\u003EGeorgia Institute of Technology\u003Cbr \/\u003E\u003Ca href=\u0022http:\/\/jiyfeng.github.io\/\u0022 target=\u0022_blank\u0022\u003Ehttp:\/\/jiyfeng.github.io\/\u003C\/a\u003E\u003Cbr \/\u003E\u003Cbr \/\u003EDate: April 7, 2015 (Tuesday)\u003Cbr \/\u003ETime: 1:00PM \u2013 3:00PM EDT\u003Cbr \/\u003ELocation: Klaus 1212\u003Cbr \/\u003E\u003Cbr \/\u003E\u003Cstrong\u003ECommittee\u003C\/strong\u003E\u003Cbr \/\u003EDr. Jacob Eisenstein (Advisor), School of Interactive Computing, Georgia Institute of Technology\u003Cbr \/\u003EDr. Mark Riedl, School of Interactive Computing, Georgia Institute of Technology\u003Cbr \/\u003EDr. Byron Boots, School of Interactive Computing, Georgia Institute of Technology\u003Cbr \/\u003E\u003Cbr \/\u003E\u003Cbr \/\u003E\u003Cstrong\u003EAbstract:\u003C\/strong\u003E\u003Cbr \/\u003EDiscourse information is about how coherent texts are structured, and how the sentences in texts are connected with discourse relations. In natural language processing (NLP), discourse information could help NLP systems to do better jobs, for example, getting more accurate results on sentiment analysis or making machine-translated texts more fluent. However, automatically exacting discourse information is difficult, because it requires semantic information from texts. The existing representation methods with surface features are too shallow to capture enough information for processing discourse.\u003Cbr \/\u003E\u0026nbsp;\u003Cbr \/\u003EThe goal of my work is to improve the performance of discourse processing with representation learning. Instead of employing some hand-crafted surface features, I propose to learn a representation function for extracting information from texts. With supervision signals from discourse annotation, the representation function is able to learn the semantic information automatically. In this proposal, I present three representation functions with different complexities: (i) a linear function, (ii) an upward composition function with syntactic structures, and (iii) a downward composition function with the identified entities shared in texts. With representation learning, the performance of discourse processing is improved on several different tasks, including discourse parsing on the RST Discourse Treebank and implicit discourse relation identification on the Penn Discourse Treebank. Furthermore, to minimize the requirement of annotated data for representation learning, I extend the framework by introducing some learning methods with distant supervision. In addition, I also discuss two applications, sentiment analysis and discourse-aware machine translation, with the state-of-the-art discourse processing system from my completed work.\u003C\/p\u003E","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"Semantic Representation Learning for Discourse Processing"}],"uid":"27707","created_gmt":"2015-04-01 09:10:59","changed_gmt":"2016-10-08 01:45:59","author":"Tatianna Richardson","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2015-04-07T14:00:00-04:00","event_time_end":"2015-04-07T16:00:00-04:00","event_time_end_last":"2015-04-07T16:00:00-04:00","gmt_time_start":"2015-04-07 18:00:00","gmt_time_end":"2015-04-07 20:00:00","gmt_time_end_last":"2015-04-07 20:00:00","rrule":null,"timezone":"America\/New_York"},"extras":[],"groups":[{"id":"221981","name":"Graduate Studies"}],"categories":[],"keywords":[{"id":"1366","name":"defense"},{"id":"1808","name":"graduate students"},{"id":"913","name":"PhD"},{"id":"3395","name":"proposal"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1788","name":"Other\/Miscellaneous"}],"invited_audience":[{"id":"78771","name":"Public"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}