Scholar
Maunendra Sankar Desarkar
Google Scholar ID: W8LJ-tEAAAAJ
IIT Hyderabad
Citations & Impact
Citations
1,144
H-index
17
i10-index
30
Publications
20
Co-authors
14
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Aishwarya's work titled 'Probing the Inherent Ability of Large Language Models for Generating Empathetic Responses' accepted at IEEE Swiss Conference on Data Science | SDS 2025.
- Debolena's work on hallucinations in LVLM-based captioning for drone-captured data accepted in WACV 2025.
- Suvodip Dey defends his PhD Thesis, 'Towards Scalable and Interpretable Dialogue Systems and their Evaluation'.
- Suvodip's work 'BoK: Introducing Bag-of-Keywords Loss for Interpretable Dialogue Response Generation' accepted in SIGDIAL 2024.
- Work on non-toxic autosuggest generation accepted at SIGIR 2024.
- Two papers accepted at PAKDD 2024, one on non-toxic autosuggest generation and another on image captioning.
- Papers on improving zero-shot MT for extremely low resource languages using noise injection techniques accepted in EMNLP (Findings) and EACL.
- First publication from Maharaj's PhD work.
Research Experience
- Works in the Natural Language and Information Processing (NLIP) lab, focusing on advancing AI, particularly NLP techniques that can excel even in scenarios with limited labeled data, and incorporating desirable properties like non-toxicity, empathy, etc.
Background
- Associate Professor at the Computer Science and Engineering Department, IIT Hyderabad, India. Also affiliated with the AI Department at IIT Hyderabad as a faculty member. Main research areas include Natural Language Processing, Information Retrieval, and Machine Learning. Works towards advancing AI, specifically NLP algorithms that are robust, responsible, and respectful to diverse audiences speaking different languages and following various cultures.
