Soumya Chatterjee

soumyac [at]

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

I received my bachelor’s in Computer Science from IIT Bombay. In the past, I was an AI Resident at Google Research and have done internships at Apple, Google Research, AWL and GreyAtom.

My research interests include Natural Language Processing and Systems for Machine Learning.

Share your thoughts or feedback with me (anonymously) here.


Apr 2024
Teaching assistant for CS 224N again in Spring 24
Jan 2024
Teaching assistant for CS 224N Natural Language Processing with Deep Learning (Winter 24)
Sep 2023
Teaching assistant for CS 236 Deep Generative Models (Fall 23)
Jun 2023
Started internship at Apple in the Machine Translation team
Jun 2023
New preprint on information retrieval from different data sources
Sep 2022
Started working on FlexFlow
Sep 2022
Started MS in Computer Science at Stanford University
Apr 2022
Paper improving re-estimation reliability of human behavioural metrics via temporal modelling 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
Jul 2021
Joined Google Research as an AI Resident
May 2020
Started internship at Google Research India
Dec 2019
Started internship at AWL Inc
Sep 2019
Paper on Thermal Face Recognition to appear at MMM 2020
May 2019
Started internship at National Chung Cheng University
Nov 2018
Started internship at GreyAtom EduTech


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
Resources and Evaluations for Multi-Distribution Dense Information Retrieval
Matching options to tasks using Option-Indexed Hierarchical Reinforcement Learning