Biography

I am a fifth-year Ph.D. Candidate at the Computer Science Department of the University of Maryland, College Park. I work with my advisor Marine Carpuat and other members of the CLIP lab. My research focuses on Machine Translation, Natural Language Generation and its evaluation.

This past summer, I interned with Marjan Ghazvininejad at MetaAI. I spent the last two summers at Google Research working with Julia Kreutzer, George Foster, Colin Cherry and Markus Freitag on problems related to Non-autoregressive Machine Translation and Reference-free Evaluation.

Education

  • PhD in Computer Science, 2023

    University of Maryland

  • Masters in Computer Science, 2020

    University of Maryland

  • B.Tech. in Computer Science and Engineering, 2017

    Indian Institute of Technology Guwahati

Publications

Sweta Agrawal, Julia Kreutzer, Colin Cherry (2022). Exploring the Benefits and Limitations of Multilinguality for Non-autoregressive Machine Translation. In WMT.

Preprint

Elijah Rippeth, Sweta Agrawal, Marine Carpuat (2022). Controlling Translation Formality Using Pre-trained Multilingual Language Models. In IWSLT.

PDF Code

Sweta Agrawal, Marine Carpuat (2022). An Imitation Learning Curriculum for Text Editing with Non-Autoregressive Models. In ACL.

PDF Code Video

Eleftheria Briakou, Sweta Agrawal, Joel Tetreault, Marine Carpuat (2021). Evaluating the Evaluation Metrics for Style Transfer: A Case Study in Multilingual Formality Transfer. In EMNLP.

PDF Code

Sweta Agrawal, Weijia Xu, Marine Carpuat (2021). A Non-Autoregressive Edit-Based Approach to Controllable Text Simplification. In Findings ACL.

PDF Code Video

See all publications

Contact

  • Room 4108, 8223 Paint Branch Dr., College Park, MD 20742