{"638840":{"#nid":"638840","#data":{"type":"event","title":"Dungeons and Discourse: Using Computational Storytelling to Look at Natural Language Use with Lara Martin","body":[{"value":"\u003Cp\u003E\u003Cstrong\u003ESpeaker:\u0026nbsp;\u003C\/strong\u003ELara\u0026nbsp;J. Martin\u003Cbr \/\u003E\r\n\u003Cstrong\u003ETime:\u0026nbsp;\u003C\/strong\u003E09\/11\/2020, 12.30pm - 1.30pm\u003Cbr \/\u003E\r\n\u003Cstrong\u003ELocation\u003C\/strong\u003E:\u0026nbsp;\u003Ca href=\u0022https:\/\/primetime.bluejeans.com\/a2m\/live-event\/gdakksqz\u0022 id=\u0022LPlnk\u0022 target=\u0022_blank\u0022\u003Ehttps:\/\/primetime.bluejeans.com\/a2m\/live-event\/gdakksqz\u003C\/a\u003E\u003C\/p\u003E\r\n\r\n\u003Ch4\u003E\u003Cstrong\u003ETitle:\u0026nbsp;\u003C\/strong\u003E\u003C\/h4\u003E\r\n\r\n\u003Cp\u003EDungeons and Discourse: Using Computational Storytelling to Look at Natural Language Use\u003C\/p\u003E\r\n\r\n\u003Ch4\u003E\u003Cstrong\u003EAbstract:\u003C\/strong\u003E\u003C\/h4\u003E\r\n\r\n\u003Cp\u003EAlthough we are currently riding a technological wave of personal assistants, many of these agents still struggle to communicate appropriately. Humans are natural storytellers, so it would be fitting if artificial intelligence could tell stories as well. Automated story generation is an area of AI research that aims to create agents that tell \u0026ldquo;good\u0026rdquo; stories. Previous story generation systems use planning and discrete symbols to create new stories, but these systems require a vast amount of knowledge engineering. The stories created by these systems are coherent, but only a finite set of stories can be generated. In contrast, very large neural language models, such as transformers, have made the headlines in the natural language processing community. Though impressive on the surface, these models begin to lose coherence over time. My research looks at various techniques of automated story generation, culminating in the blend of symbolic and neural approaches. In this talk, I show how a neuro-symbolic model can provide more\u0026nbsp;interesting\u0026nbsp;and\u0026nbsp;coherent stories than those from solely neural or symbolic systems.\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Ch4\u003E\u003Cstrong\u003EBio:\u003C\/strong\u003E\u003C\/h4\u003E\r\n\r\n\u003Cp\u003ELara\u0026nbsp;J. Martin is a Human-Centered Computing Ph.D. Candidate in the College of Computing at Georgia Tech. Her work resides in the field of Human-Centered Artificial Intelligence with a focus on natural language applications.\u0026nbsp;Lara\u0026nbsp;has worked in the areas of automated story generation, speech processing, and affective computing, publishing in top-tier conferences such as AAAI and IJCAI.\u0026nbsp;Lara\u0026nbsp;earned a Masters of Language Technologies from Carnegie Mellon University in 2015 and a BS in Computer Science \u0026amp; Linguistics from Rutgers University-New\u0026nbsp;Brunswick in 2013. In 2019, she received Georgia Tech\u0026rsquo;s prestigious\u0026nbsp;\u003Ca href=\u0022https:\/\/gvu.gatech.edu\/gvu-graduate-student-awards-program-2019\u0022 rel=\u0022noopener noreferrer\u0022 target=\u0022_blank\u0022\u003EFoley Scholar Award\u003C\/a\u003E\u0026nbsp;for her innovative research and the Best Doctoral Consortium Presentation award at the 2019 ACM Richard Tapia Celebration of Diversity in Computing Conference. As a\u0026nbsp;\u003Ca href=\u0022https:\/\/cifellows2020.org\/\u0022 rel=\u0022noopener noreferrer\u0022 target=\u0022_blank\u0022\u003E2020 Computing Innovation Fellowship\u003C\/a\u003E\u0026nbsp;recipient, she will be joining Dr. Chris Callison-Burch as a postdoctoral researcher at the University of Pennsylvania. She has also been featured in\u0026nbsp;\u003Ca href=\u0022https:\/\/www.wired.com\/story\/forget-chess-real-challenge-teaching-ai-play-dandd\/\u0022 rel=\u0022noopener noreferrer\u0022 target=\u0022_blank\u0022\u003EWired\u003C\/a\u003E.\u0026nbsp;\u003C\/p\u003E\r\n","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"NLP and AI seminar hosted by ML@GT students"}],"uid":"34773","created_gmt":"2020-09-08 17:22:33","changed_gmt":"2020-09-10 14:05:17","author":"ablinder6","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2020-09-11T13:30:00-04:00","event_time_end":"2020-09-11T14:30:00-04:00","event_time_end_last":"2020-09-11T14:30:00-04:00","gmt_time_start":"2020-09-11 17:30:00","gmt_time_end":"2020-09-11 18:30:00","gmt_time_end_last":"2020-09-11 18:30:00","rrule":null,"timezone":"America\/New_York"},"extras":[],"groups":[{"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":"174045","name":"Graduate students"},{"id":"78751","name":"Undergraduate students"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}