Leveraging Speaker Context for Natural Language Processing

Leveraging Speaker Context for Natural Language Processing (via Zoom)

Abstract: Though neural networks have allowed for advances in modeling linguistic content through Natural Language Processing, capturing the effects of contextual information, such as speaker gender or role, on NLP tasks is still an open area of research. In this talk, we first explore how such context can affect a system’s performance. Next, we investigate methods for incorporating additional context into such a system. Finally, we develop approaches for building a system that uses auxiliary contextual information when the signal is sparse.

Bio: Samee Ibraheem is a PhD student in Computer Science at UC Berkeley advised by Professor John DeNero. His research interests lie in integrating speaker attribute information into NLP systems, with a focus on applications that are relevant to online security. Samee has been awarded the NSF Graduate Research Fellowship, the UC Berkeley Chancellor’s Fellowship, and previously received a Bachelor’s magna cum laude in Neurobiology with a minor in Computer Science from Harvard University.