Conversational AI at Facebook
Conversational systems like Siri and Google Assistant have been around for several years now; and have recently started to play increasingly ubiquitous roles in people's daily lives, through smart home devices, phones, or social media (like Messenger). Despite this, the conversational experience that these systems provide has evolved only incrementally. At the same time, however, interest in conversational AI from the research community is growing fast, and there’s more potential than ever for using machine learning to power these systems. In this talk, I'll cover some lessons learned from research in making these systems more engaging and natural.
Anusha is a research engineer at Facebook on the Conversational AI team. She conducts research on building better conversational systems, with a specific focus on Natural Language Generation (NLG) and dialogue policy. Previously, she was a Master's student at Stanford University, where she studied Artificial Intelligence with a special focus on Natural Language Processing, and worked on research projects with Dr. Percy Liang at the Stanford NLP group. She also previously worked at Siri, where she built semantic parsing models for Siri and Spotlight Search