Building AI systems that can process user input, understand it, and generate an engaging and contextually-relevant output in response, has been one of the longest-running goals in AI. Humans use a variety of modalities, such as language and visual cues, to communicate. A major trigger to our meaningful communications are "events" and how they cause/enable future events. In this talk, I will present my research about language comprehension and language generation around events, with a major focus on commonsense reasoning, world knowledge, and context modeling. I will focus on multiple context modalities such as narrative, conversational, and visual. Finally, I will highlight my recent work on language comprehension in the biomedical domain for finding cures for major diseases.
Nasrin Mostafazadeh is a senior research scientist at BenevolentAI labs. She recently got her PhD at the University of Rochester working with James Allen in conversational interaction and dialogue research group. During her PhD, she spent about a year at Microsoft and a summer at Google doing research on various NLP problems. Nasrin’s research focuses on language comprehension, mainly studying events to predict what happens next. She has developed models for tackling various research tasks for pushing AI toward deeper language understanding with applications ranging from story generation to vision & language. Recently, she has been working on language comprehension in the biomedical domain, with the goal of finding cures for major diseases such as cancer by leveraging millions of unstructured data.