Curriculum Vitae

View PDF
saujasv.github.io
svadugur [AT] cs [DOT] cmu [DOT] edu
saujasv

Education

Ph.D. in Language and Information Technologies, 2022–present
Language Technologies Institute, School of Computer Science, Carnegie Mellon University
Advisor: Daniel Fried
B.Tech. in Computer Science and M.S. (by Research) in Computational Linguistics, 2017–2022
International Institute of Information Technology (IIIT), Hyderabad
Advisors: Monojit Choudhury, Dipti Misra Sharma
Thesis: Program Synthesis for Linguistic Rules

Former Positions

Research Assistant, Language Technologies Research Center, IIIT, Hyderabad, 2019–2022
Research Intern, Chandar Research Lab, Mila, May–Aug 2021
Advisors: Sarath Chandar, Prasanna Parthasarathi

Publications

  1. Generating Pragmatic Examples to Train Neural Program Synthesizers
    Saujas Vaduguru, Daniel Fried, Yewen Pu
    Twelfth International Conference on Learning Representations (ICLR), 2024.

  2. Symbolic Planning and Code Generation for Grounded Dialogue
    Justin T. Chiu, Wenting Zhao, Derek Chen, Saujas Vaduguru, Alexander M. Rush, Daniel Fried
    Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023.

  3. Amortizing Pragmatic Program Synthesis with Rankings
    Yewen Pu, Saujas Vaduguru, Priyan Vaithilingam, Elena Glassman, Daniel Fried
    arXiv preprint, 2023.

  4. Adapting to Gradual Distribution Shifts with Continual Weight Averaging
    Jared Fernandez, Saujas Vaduguru, Sanket Vaibhav Mehta, Yonatan Bisk, Emma Strubell
    Workshop on High-dimensional Learning Dynamics
    40th International Conference on Machine Learning (ICML), 2023.

  5. Probing Negation in Language Models
    Shashwat Singh, Shashwat Goel, Saujas Vaduguru, Ponnurangam Kumaraguru
    8th Workshop on Representation Learning for NLP (RepL4NLP)
    61st Annual Meeting of the Association for Computational Linguistics (ACL), 2023.

  6. Stress Rules from Surface Forms
    Saujas Vaduguru, Partho Sarthi, Dipti Misra Sharma, Monojit Choudhury
    International Conference on Natural Language Processing (ICON), 2021.

  7. Efficient Pragmatic Program Synthesis with Informative Specifications
    Saujas Vaduguru, Kevin Ellis, Yewen Pu
    Workshop on Meaning in Context: Pragmatic Communication in Humans and Machines
    35th Conference on Neural Information Processing Systems (NeurIPS), 2021.
    [talk], [code]

  8. Sample-efficient Linguistic Generalizations through Program Synthesis: Experiments with Phonology Problems
    Saujas Vaduguru, Aalok Sathe, Monojit Choudhury, Dipti Misra Sharma
    Proceedings of the 18th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology
    The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP), 2021.
    [dataset]

Honors and Awards

Mitacs Globalink Research Internship, 2021
Dean's List Award for Academic Performance, IIIT Hyderabad, 2017–21
Honourable Mention, International Linguistics Olympiad, 2015

Academic Service

Reviewer: ICON 2021, NILLI@EMNLP 2021, ACL 2023, EMNLP 2023, BlackboxNLP@EMNLP 2023

Teaching

Teaching Assistant, Advanced Natural Language Processing, Carnegie Mellon University, Fall 2023
Teaching Assistant, Computational Linguistics I, IIIT, Hyderabad, Spring 2020

Invited Talks

Program synthesis from informative examples, CMU Software Research Seminar, Fall 2023

Outreach

Panini Linguistics Olympiad
  • Co-chair of Problem Committee and Jury, and member of the Organizing Committee for the Indian national Linguistics Olympiad program from 2018–2021
  • Team leader and coach for Indian team at the International Linguistics Olympiad in 2018, 2019, and 2021
  • Lecturer at Joint Asian-Pacific Linguistics Training, 2021–22