Jyotsana Khatri
Research Scholar
Indian Institute of Technology Bombay
About me
Hi, I am a PhD student in the Department of Computer Science and Engineering at Indian Institute of Technology (IIT), Bombay working with Prof. Pushpak Bhattacharyya .
My research focuses on deep learning techniques for various NLP tasks in low resource scenarios, especially for Indian Languages. I am currently exploring cross-lingual word embeddings and Unsupervised Machine Translation for Indian Languages.
Interests
- Machine Translation
- Cross-lingual embeddings
- Meta Learning
Education
PhD (2017-2022)
Indian Institute of Technology Bombay
M.Tech. (Machine Learning) (2016)
DAIICT, Gandhinagar
Publications
(2021).
Simple Measures of Bridging Lexical Divergence Help Unsupervised Neural Machine Translation for Low-Resource Languages.
JMT, Dec 2021.
(2021).
Language model pre-training and transfer learning for very low resource languages.
WMT 2021.
(2021).
Language Relatedness and Lexical Closeness can help Improve Multilingual NMT: IITBombay@ MultiIndicNMT WAT2021.
WAT 2021.
(2020).
A Study of Efficacy of Cross-lingual Word Embeddings for Indian Languages.
CoDS-COMAD 2020.
(2020).
Filtering Back-Translated Data in Unsupervised Neural Machine Translation.
Proceedings of the 28th International Conference on Computational Linguistics, pages 4334–4339 Barcelona, Spain (Online), December 8-13, 2020.