Maharaj Brahma
Scholar

Maharaj Brahma

Google Scholar ID: g-i3MXwAAAAJ
Indian Institute of Technology Hyderabad (IITH)
Natural Language ProcessingCulture NLPLow-resource MTMultilingual NLP
Citations & Impact
All-time
Citations
93
 
H-index
6
 
i10-index
4
 
Publications
20
 
Co-authors
3
list available
Resume (English only)
Research Experience
  • Before joining the Ph.D. program, served as a Teaching Assistant (TA) for Advanced Computer Network Lab (PCSE271) and Programming for Problem Solving Lab (UCSE271) at CITK, and also as a TA for Mobile and Pervasive Computing (PCSE115) instructed by Prof. Pranav Kumar Singh.
  • Co-founded a startup “DigitalOma” with friends in 2020.
  • Completed a thesis titled “English-Bodo Neural Machine Translation using Attention Mechanism” in 2019.
  • Submitted MT system ranked first for MultiIndic22MT shared task at WMT 24 in October 2024.
  • Gave Research Proposal Seminar (RPS) in September 2024.
  • Paper titled “MorphTok: Morphologically Grounded Tokenization for Indic languages” accepted at Tokenization Workshop (TokShop) @ ICML 2025 in July 2025.
  • Paper titled “DIWALI - Diversity and Inclusivity aWare cuLture specific Items for India: Dataset and Assessment of LLMs for Cultural Text Adaptation in Indian Context” accepted at EMNLP 2025 in September 2025.
  • Will be presenting a poster at IndoML 2025 in October 2025.
  • Paper “DIWALI - Diversity and Inclusivity aWare cuLture specific Items for India: Dataset and Assessment of LLMs for Cultural Text Adaptation in Indian Context” selected for an oral presentation at EMNLP 2025 in October 2025.
Background
  • Research interests: Culture NLP, Multilingual NLP, and Machine Translation. Interested in building resources for low-resource languages.
Miscellany
  • Interested in localization for Bodo language. Join Bodo Mozilla Pontoon team!