Natural Language Processing

Understanding human languages has been a cornerstone application of AI. NLP Group at ScAI focuses on two salient research agendas. First, it builds AI systems that process information expressed in text via information extraction, and share this information to users through question answering and dialog systems. The group is known for its influential work in open information extraction, where information is extracted in open schema. Second, ScAI has initiated a massive effort in building multilingual NLP systems for machine translation, information extraction and knowledge base completion. One focus of the group is on translation among Indian languages, which are low-resource. Use of massive language models trained on Indian language datasets in conjunction with syntactic processing of text might suggest a solution for Indian language machine translation. The group also expects to use this technology in context of various applications such as healthcare, law and education.

Impact Areas

Information Extraction
Question Answering
Dialog Systems
Machine Translation
Summarization
Multilinguality

Faculty Members Currently ​​​​​​​Involved

Mausam
Parag Singla
Tanmoy Chakraborty
Ashwini Vaidya

Key Publications

    Parthiv Chatterjee Asish Batha Tashvi Patel Sourish Dasgupta Tanmoy Chakraborty. Beyond Markovian Drifts: Action-Biased Geometric Walks with Memory for Personalized Summarization. Published in ICLR, 2026.
    PDFCite
    Parthiv Chatterjee, Dhara Jhaveri, Sourish Dasgupta, Tanmoy Chakraborty. IMPerSumm: Information-Modulated User Preference Modeling for Personalized Text Summarization. Published in The Web Conference, 2026.
    PDFCite
    Sahil Mishra, Srinitish Srinivasan, Srikanta Bedathur, Tanmoy Chakraborty. TaxoBell: Gaussian Box Embeddings for Self-Supervised Taxonomy Expansion. Published in The Web Conference, 2026.
    PDFCite
    Prottay Kumar Adhikary, Reena Rawat, Tanmoy Chakraborty. coTherapist: A Behavior-Aligned Small Language Model Framework to Support Mental Healthcare Experts. Published in The Web Conference, 2026.
    PDFCite
    Amey Hengle, Prasoon Bajpai, Soham Dan, Tanmoy Chakraborty. Can LLMs Reason over Extended Multilingual Contexts? Towards Long-Context Evaluation Beyond Retrieval over Haystacks. Published in EACL, 2026.
    PDFCite
    Ashutosh Bajpai, Akshat Bhandari, Akshay Nambi, Tanmoy Chakraborty. SpatialMath: Spatial Comprehension-Infused Symbolic Reasoning for Mathematical Problem-Solving. Published in EACL (Findings), 2026.
    PDFCite
    Sahil Mishra, Avi Patni, Niladri Chatterjee, Tanmoy Chakraborty. QuanTaxo: A Quantum Approach to Self-Supervised Taxonomy Expansion. Published in AAAI, 2026.
    PDFCite
    Ayan Sengupta, Yash Goel, Tanmoy Chakraborty. How to Upscale Neural Networks with Scaling Law?. Published in TMLR, 2025.
    PDFCite
    Parthiv Chatterjee, Shivam R Sonawane, Amey Hengle, Aditya Tanna, Sourish Dasgupta, Tanmoy Chakraborty. Diversity Augmentation of Dynamic User Preference Data for Boosting Personalized Text Summarizers. Published in TMLR, 2025.
    PDFCite
    Ayan Sengupta, Siddhant Chaudhary, Tanmoy Chakraborty. Value-Guided KV Compression for LLMs via Approximated CUR Decomposition. Published in NeurIPS, 2025.
    PDFCite
    Aishik Mandal, Tanmoy Chakraborty, Iryna Gurevych, Towards Privacy-aware Mental Health AI Models: Advances, Challenges. and Opportunities. Published in Nature Computational Science, 2025.
    PDFCite
    Namrata Bhattacharya, Swagatam Chakraborti, Stuti Kumari, Bernadette Mathew, Abhishek Halder, Sakshi Gujral, Krishan Gupta, Aayushi Mittal, Debajyoti Sinha, Colleen Nelson, Tanmoy Chakraborty, Gaurav Ahuja, Debarka Sengupta. Network based simultaneous embedding of cells and marker genes from scRNA-seq studies. Published in Briefings in Bioinformatics, 2025.
    PDFCite
    Challenges and Propositions. Published in Knowledge-Based Systems, 2025..
    PDFCite
    Bhavyaa Dave, Priya Martin, Sharel Singh David, Saravana Kumar, Tanmoy Chakraborty. Enhancing Healthcare Worker Mental Health via Artificial Intelligence-Driven Work Process Improvements: A Scoping Review. Published in International Journal of Medical Informatics, 2025.
    PDFCite
    Arghodeep Nandi, Megha Sundriyal, Euna Mehnaz Khan, Jikai Sun, Emily K. Vraga, Jaideep Srivastava, Tanmoy Chakraborty. The Psychology of Falsehood: A Human-Centric Survey of Misinformation Detection. Published in EMNLP, 2025.
    PDFCite
    Eshaan Tanwar, Anwoy Chatterjee, Michael Saxon, Alon Albalak, William Yang Wang, Tanmoy Chakraborty. Do You Know About My Nation? Investigating Multilingual Language Models’ Cultural Literacy Through Factual Knowledge. Published in EMNLP, 2025.
    PDFCite
    Maithili Joshi, Palash Nandi, Tanmoy Chakraborty. SABER: Uncovering Vulnerabilities in Safety Alignment via Cross-Layer Residual Connection. Published in EMNLP, 2025.
    PDFCite
    Ashutosh Bajpai, Tanmoy Chakraborty. Temporal Referential Consistency: Do LLMs Favor Sequences Over Absolute Time References?. Published in EMNLP, 2025.
    PDFCite
    Joykirat Singh, Subhabrata Dutta, Tanmoy Chakraborty. Data-scarce Behavior Editing of Language Models. Published in EMNLP, 2025.
    PDFCite
    Wenchao Dong, Megha Sundriyal, Seongchan Park, Jaehong Kim, Meeyoung Cha, Tanmoy Chakraborty, Wonjae Lee. Parallel Communities Across the Surface Web and the Dark Web. Published in EMNLP, 2025.
    PDFCite