Shrey Desai

[cv] [email] [github]

About Me

I'm a fourth-year computer science undergraduate at The University of Texas at Austin, where I work with Jessy Li and Greg Durrett. Previously, I was a software engineering intern at Facebook Conversational AI, Uber, and Microsoft. My research primarily focuses on natural language processing and deep learning. Specifically, I'm interested in low-resource learning -- developing methods that use less resources (e.g., data, compute, memory), show robustness under distributional shifts, and generalize to unseen domains. I'm also interested in computational social science and machine learning for social good.


Talks

Investigating Domains in Low-Resource NLP
Computational Linguistics with Minimal Supervision Seminar, 2019
[slides]


Publications

Evaluating Lottery Tickets Under Distributional Shifts
Shrey Desai, Hongyuan Zhan, Ahmed Aly
EMNLP 2019 Workshop on Deep Learning for Low-Resource NLP, 2019 (oral)
[paper] [code] [slides]

Adaptive Ensembling: Unsupervised Domain Adaptation for Political Document Analysis
Shrey Desai, Barea Sinno, Alex Rosenfeld, Junyi Jessy Li
Empirical Methods in Natural Language Processing (EMNLP), 2019
[paper] [code]


Awards

Empirical Methods in Natural Language Processing (EMNLP) Student Scholarship (2019)
Lala Fay & Claude DeVan Watts Endowed Presidential Scholarship (2019)