People

Sonal Gupta

Research Scientist

I am a research scientist working on conversational AI systems. I completed my PhD at Stanford University in 2015 where I worked with Chris Manning on weakly supervised and interpretable information extraction. Prior to that, I finished my Master’s at University of Texas at Austin where I worked with Raymond Mooney and Kristen Grauman on combining language and vision modes for information extraction. Before joining FB, I developed deep learning models for conversational AI systems at Viv, a startup later acquired by Samsung.

Interests

Natural language processing, machine learning and conversational AI systems

Latest Publications

EMNLP - November 9, 2020

Sound Natural: Content Rephrasing in Dialog Systems

Arash Einolghozati, Anchit Gupta, Keith Diedrick, Sonal Gupta

EMNLP - October 7, 2020

Low-Resource Domain Adaptation for Compositional Task-Oriented Semantic Parsing

Xilun Chen, Asish Ghoshal, Yashar Mehdad, Luke Zettlemoyer, Sonal Gupta

December 14, 2018

PyText: A seamless path from NLP research to production

Ahmed Aly, Kushal Lakhotia, Shicong Zhao, Mrinal Mohit, Barlas O─čuz, Abhinav Arora, Sonal Gupta, Christopher Dewan, Stef Nelson-Lindall, Rushin Shah

Conversational AI Workshop at NeurIPS 2018 - December 4, 2018

Improving Semantic Parsing for Task Oriented Dialog

Arash Einolghozati, Panupong Pasupat, Sonal Gupta, Rushin Shah, Mrinal Mohit, Mike Lewis, Luke Zettlemoyer

NAACL - December 4, 2018

Cross-lingual Transfer Learning for Multilingual Task Oriented Dialog

Sebastian Schuster, Sonal Gupta, Rushin Shah, Mike Lewis

EMNLP 2018 - October 31, 2018

Semantic Parsing for Task Oriented Dialog using Hierarchical Representations

Sonal Gupta, Rushin Shah, Mrinal Mohit, Anuj Kumar, Mike Lewis