Abigail See will be giving a virtual talk on Friday, September 18th from 11am — 12pm. Zoom information will be distributed via the Berkeley NLP Seminar listserv.
Title: Neural Generation Meets Real People: Towards Emotionally Engaging Mixed-Initiative Conversations
Abstract: In this talk I will present Chirpy Cardinal, an open-domain dialogue agent built by the Stanford NLP team in 2019 Alexa Prize competition. Building an open-domain socialbot that talks to real people is challenging – such a system must meet multiple user expectations such as broad world knowledge, conversational style, and emotional connection. Our socialbot engages users on their terms – prioritizing their interests, feelings and autonomy. As a result, our socialbot provides a responsive, personalized user experience, capable of talking knowledgeably about a wide variety of topics, as well as chatting empathetically about ordinary life. Neural generation plays a key role in achieving these goals, providing the backbone for our conversational and emotional tone. Chirpy Cardinal ultimately won 2nd place in the competition final, with a 3.6/5.0 average customer rating.
Bio: Abigail See is a PhD student in the Stanford Natural Language Processing group, advised by Professor Christopher Manning. Her research focuses on improving the controllability, interpretablility and coherence of neural NLG in open-ended settings such as story generation and chitchat dialogue. At Stanford, she has been the co-instructor of CS224n: Natural Language Processing with Deep Learning, and the organizer of AI Salon, a discussion forum for AI. Twitter: @abigail_e_see.