Show simple item record

dc.contributor.authorBansal, Mohit
dc.date.accessioned2018-11-27T16:07:22Z
dc.date.available2018-11-27T16:07:22Z
dc.date.issued2018-11-19
dc.identifier.urihttp://hdl.handle.net/1853/60565
dc.descriptionPresented on November 19, 2018 at 12:15 p.m. in the Marcus Nanotechnology Building, Room 1116.en_US
dc.descriptionMohit Bansal is the Director of the UNC-NLP Lab (nlp.cs.unc.edu) and an assistant professor in the Computer Science department at University of North Carolina (UNC) Chapel Hill. His research expertise is in statistical natural language processing and machine learning, with a particular focus on multimodal, grounded, and embodied semantics (i.e., language with vision and speech, for robotics), human-like language generation and Q&A/dialogue, and interpretable and generalizable deep learning.en_US
dc.descriptionRuntime: 58:52 minutesen_US
dc.description.abstractIn this talk, I will discuss my group's recent work on state-of-the-art natural language generation (NLG) and dialogue models that are multimodal, personality-based, and knowledge-rich. First, we will discuss dialogue models which generate responses that are not only history-relevant and fluent, but also multimodal, e.g., relevant to dynamic video-based context. Next, we will present personality-based conversational agents, e.g., models that generate stylistic responses with varying levels of politeness and rudeness. Finally, we will describe several directions in making NLG models more knowledgeable, e.g., via adversarial robustness to user errors, via filling reasoning gaps in multi-hop generative-QA with external commonsense knowledge, and via multi-task and reinforcement learning with novel auxiliary-skill tasks such as entailment and saliency generation.en_US
dc.format.extent58:52 minutes
dc.language.isoen_USen_US
dc.relation.ispartofseriesMachine Learning@Georgia Tech Seminar Seriesen_US
dc.subjectDialogue modelsen_US
dc.subjectNatural language generation (NLG)en_US
dc.subjectPersonality-based agentsen_US
dc.titleMultimodal, Personable, and Knowledgeable Language Generationen_US
dc.typeLectureen_US
dc.typeVideoen_US
dc.contributor.corporatenameGeorgia Institute of Technology. Machine Learningen_US
dc.contributor.corporatenameUniversity of North Carolina at Chapel Hill. Dept. of Computer Scienceen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record