Skip to main content

Unleashing the Power of Data through Neurosymbolic Program Synthesis

Jocelyn Chen

PhD Candidate, University of Texas at Austin

Abstract: In today’s data-rich world, there is a growing need for tools that can help people extract, query, and utilize this data in an effective manner. This talk will focus on programming abstractions and synthesis algorithms that help people unleash the power of data by facilitating convenient data extraction and visualization. From a technical perspective, the talk will showcase synergies between programming languages tools (such as type systems and program analysis) and modern NLP techniques, and it will shed light on how this synergy enables a new science of neurosymbolic programming.

Bio: Jocelyn (Qiaochu) Chen is a PhD candidate at the University of Texas at Austin advised by Isil Dillig and Greg Durrett. She works at the intersection of programming languages and natural language processing. She aims to develop innovative techniques that combine the convenience and transparency of programming languages with the powerful capabilities of modern deep-learning techniques.