Soumya Chatterjee

MS CS at Stanford University

About Me

I am a Master’s student in Computer Science at Stanford University.

Previously, I was a Pre-Doctoral Researcher at Google Research. I graduated from IIT Bombay with B.Tech in Computer Science and a Minor in Statistics.

My research interests include Machine Learning, Natural Language Processing, and Representation Learning. I am currently excited about knowledge augmented and retrieval-based methods for NLP, question answering, and symbolic reasoning over neural representations.

During my bachelor’s, I was fortunate to be advised by Prof. Sunita Sarawagi and Prof. Preethi Jyothi. I had also worked closely with Prof. Ganesh Ramakrishnan and Prof. Soumen Chakrabarti.

I have done internships at Google Research India on modeling human behavior, AWL Inc. on object detection, GreyAtom EduTech on developing NLP course assignments and projects, and with Prof Wei-Ta Chu on thermal face recognition.

Soumya Chatterjee

MS CS at Stanford University


Sept 2022
Started MS in Computer Science at Stanford University
Apr 2022
Paper on improving across-session estimation reliability of behavioural metrics via modelling temporal adjustment of policies to appear at CogSci 2022
Feb 2022
Paper on word alignments and use in lexically contrained translation to appear at ACL 2022
Aug 2021
Graduated from IIT Bombay with a B.Tech in Computer Science
July 2021
Joined Google Research in Bangalore, India as a Pre-Doctoral Researcher
May 2020
Started internship at Google Research India with Pradeep Shenoy
Dec 2019
Started internship at AWL Inc., Sapporo, Japan
Sept 2019
Paper on Thermal Face Recognition to appear at International Conference on Multimedia Modeling, MMM 2020
May 2019
Started internship at National Chung Cheng University with Prof. Wei-Ta Chu
Nov 2018
Started internship at GreyAtom EduTech, Mumbai, India


Accurate Online Posterior Alignments for Principled Lexically-Constrained Decoding
Meta-Learning of Dynamic Policy Adjustments in Inhibitory Control Tasks
Joint Learning of Hyperbolic Label Embeddings for Hierarchical Multi-label Classification
Model-agnostic Fits for Understanding Information Seeking Patterns in Humans
Thermal Face Recognition Based on Transformation by Residual U-Net and Pixel Shuffle Upsampling
Matching options to tasks using Option-Indexed Hierarchical Reinforcement Learning