Biography

I am a fourth-year Computer Science Ph.D. Student at the Center for Language and Speech Processing at Johns Hopkins University, supervised by Kevin Duh and Kenton Murray.

Previously, I was at Yale University studying math and computer science, and working with Dragomir Radev at the Yale LILY Lab. During Summer 2023, I interned with Maha Elbayad at Meta AI Research in Menlo Park, CA.

Interests
  • Machine Translation
  • Multilingual Representation Learning
  • Model Compression
  • Efficient NLP
Education

  • PhD in Computer Science, 2021-present

    Johns Hopkins University

  • BSc in Computer Science & Mathematics, 2017-2021

    Yale University

Recent Publications

Neha Verma, Kenton Murray, Kevin Duh
October, 2024 preprint
Merging Feed Forward Sublayers for Compressed Transformers

PDF
Neha Verma, Maha Elbayad
July, 2024 HiLD@ICML 2024, TMLR 2024
Merging Text Transformer Models from Different Initializations

PDF Code
Neha Verma, Kenton Murray, Kevin Duh
May, 2024 LREC-COLING 2024
Exploring Representational Disparities Between Multilingual and Bilingual Translation Models

PDF
Elizabeth Salesky, Neha Verma, Phillip Koehn, Matt Post
December, 2023 EMNLP 2023
Multilingual Pixel Representations for Translation and Effective Cross-lingual Transfer

PDF
Amir Hussein, Cihan Xiao, Neha Verma, Thomas Thebaud, Matthew Wiesner, Sanjeev Khudanpur
July, 2023 IWSLT 2023
JHU IWSLT 2023 Dialect Speech Translation System Description

PDF
Henry Li Xinyuan, Neha Verma, Bismarck Bamfo Odoom, Ujvala Pradeep, Matthew Wiesner, Sanjeev Khudanpur
July, 2023 IWSLT 2023
JHU IWSLT 2023 Multilingual Speech Translation System Description

PDF
Kelly Marchisio, Neha Verma, Kevin Duh, Philipp Koehn
December, 2022 EMNLP 2022
IsoVec: Controlling the Relative Isomorphism of Word Embedding Spaces

PDF Code
Irene Li, Jessica Pan, Jeremy Goldwasser, Neha Verma, Wai Pan Wong, Muhammed Yavuz Nuzumlalı, Benjamin Rosand, Yixin Li, Matthew Zhang, David Chang, R Andrew Taylor, Harlan M Krumholz, Dragomir Radev
November, 2022 Computer Science Review
Neural Natural Language Processing for unstructured data in electronic health records: A review

PDF
Neha Verma, Kenton Murray, Kevin Duh
September, 2022 AMTA 2022
Strategies for Adapting Multilingual Pre-training for Domain-Specific Machine Translation

PDF
Linyong Nan, Chiachun Hsieh, Ziming Mao, Xi Victoria Lin, Neha Verma, Rui Zhang, Wojciech Kryściński, Nick Schoelkopf, Riley Kong, Xiangru Tang, Mutethia Mutuma, Ben Rosand, Isabel Trindade, Renusree Bandaru, Jacob Cunningham, Caiming Xiong, Dragomir Radev
January, 2022 TACL 2022
FeTaQA: Free-form Table Question Answering

PDF Code
Linyong Nan, Dragomir Radev, Rui Zhang, Amrit Rau, Abhinand Sivaprasad, Chiachun Hsieh, Xiangru Tang, Aadit Vyas, Neha Verma, Pranav Krishna, Yangxiaokang Liu, Nadia Irwanto, Jessica Pan, Faiaz Rahman, Ahmad Zaidi, Mutethia Mutuma, Yasin Tarabar, Ankit Gupta, Tao Yu, Yi Chern Tan, Xi Victoria Lin, Caiming Xiong, Richard Socher, Nazneen Fatema Rajani
June, 2021 NAACL 2021
DART: Open-Domain Structured Data Record to Text Generation

PDF Code
Rui Zhang, Caitlin Westerfield, Sungrok Shim, Garrett Bingham, Alexander Fabbri, William Hu, Neha Verma, Dragomir Radev
July, 2019 ACL 2019
Improving Low-Resource Cross-lingual Document Retrieval by Reranking with Deep Bilingual Representations

PDF

Recent Posts

Understanding CKA
Explaining Centered Kernel Alignment (CKA) in more detail, and working out some of the derivations from the original Kornblith et al. paper.
Neha Verma
Oct 4, 2024
Understanding CKA

Contact

  • nverma7 (at) jhu (dot) edu
  • DM Me