* Name and title

Mitesh Khapra

Dr.

* Affiliation

Indian Institute of Technology Madras

* Title of the invited talk

IndicTrans2: Towards High-Quality and Accessible Machine Translation Models for all 22 Scheduled Indian Languages

* Abstract of the invited talk

India has a rich linguistic landscape with languages from 4 major language families spoken by over a billion people. 22 of these languages are listed in the Constitution of India (referred to as scheduled languages) and are the focus of this work. Given the linguistic diversity, high-quality and accessible Machine Translation (MT) systems are essential in a country like India. Prior to this work, there was (i) no parallel training data spanning all the 22 languages, (ii) no robust benchmarks covering all these languages and containing content relevant to India, and (iii) no existing translation models which support all the 22 scheduled languages of India. In this work, we aim to address this gap by focusing on the missing pieces required for enabling wide, easy, and open access to good machine translation systems for all 22 scheduled Indian languages. We identify four key areas of improvement: curating and creating larger training datasets, creating diverse and high-quality benchmarks, training multilingual models, and releasing models with open access. Our first contribution is the release of the Bharat Parallel Corpus Collection (BPCC), the largest publicly available parallel corpora for Indic languages. BPCC contains a total of 230M bitext pairs, of which a total of 126M were newly added, including 644K manually translated sentence pairs created as part of this work. Our second contribution is the release of the first n-way parallel benchmark covering all 22 Indian languages, featuring diverse domains, Indian-origin content, and source-original test sets. Next, we present IndicTrans2, the first model to support all 22 languages, surpassing existing models on multiple existing and new benchmarks created as a part of this work. Lastly, to promote accessibility and collaboration, we release our models and associated data with permissive licenses.

* In-person or virtual talk

Virtual

* Biography

Mitesh M. Khapra is an Associate Professor in the Department of Computer Science and Engineering at IIT Madras and is affiliated with the Robert Bosch Centre for Data Science and AI. He is also a co-founder of AI4Bharat, a voluntary community with an aim to provide AI-based solutions to India-specific problems. His research interests span the areas of Deep Learning, Multimodal Multilingual Processing, Natural Language Generation, Dialog systems, Question Answering and Indic Language Processing. He has publications in several top conferences and journals including TACL, ACL, NeurIPS, TALLIP, EMNLP, EACL, AAAI, etc. He has also served as Area Chair or Senior PC member in top conferences such as ICLR and AAAI. Prior to IIT Madras, he was a Researcher at IBM Research India for four and a half years, where he worked on several interesting problems in the areas of Statistical Machine Translation, Cross Language Learning, Multimodal Learning, Argument Mining and Deep Learning. Prior to IBM, he completed his PhD and M.Tech from IIT Bombay in Jan 2012 and July 2008 respectively. His PhD thesis dealt with the important problem of reusing resources for multilingual computation. During his PhD he was a recipient of the IBM PhD Fellowship (2011) and the Microsoft Rising Star Award (2011). He is also a recipient of the Google Faculty Research Award (2018), the IITM Young Faculty Recognition Award (2019), the Prof. B. Yegnanarayana Award for Excellence in Research and Teaching (2020) and the Srimathi Marti Annapurna Gurunath Award for Excellence in Teaching (2022).