👋Hello there, I’m Deb!
I am a Ph.D. candidate (she/her) in the Minnesota NLP group led by Prof. Dongyeop Kang at the University of Minnesota Twin Cities. I am co-supervised by Prof. Jaideep Srivastava who leads the Data Mining and Research Group (DMR) at the University of Minnesota Twin Cities. I also work as a research assistant to Prof. Jisu Huh, who heads the Minnesota Computational Advertising Laboratory (MCAL).
Broadly, my research aims to combine NLP with computational social science. Specifically, I am interested in learning about people — how user preferences, social cues, and contextual factors influence and drive user behavior — in online social media settings. I am also interested in exploring the stylistic analysis of user text content. I have adopted a variety of deep learning, natural language processing, graph, and statistical methods towards my interest in Computational Social Science.
I obtained my Master’s degree in Computer Science from the University of Minnesota, Twin Cities, and my Bachelor’s degree in Computer science from PES University, Bangalore, India.
Updates
- April 2024 - Our abstract “Beyond Words: Incorporating Graph Data into LLMs for Comprehensive Social System Analysis” is selected for oral presentation at IC2S2 2024!🥳
- April 2024 - Passed my Thesis Proposal Exam ✌🏽 One more exam to go until my defense!
- Mar 2024 - “Which Modality should I use – Text, Motif, or Image? : Understanding Graphs with Large Language Models” is accepted at NAACL 2024 Findings!🥳
- Jan 2024 - “Under the Surface: Tracking the Artifactuality of LLM-Generated Data” is finally out on ArXiv. 🆕 This paper marks my first venture as a project team lead and MinnesotaNLP’s first lab-wide project!
- Dec 2023 - Our preprint, at the intersection of Graphs and LLMS - “Which Modality should I use – Text, Motif, or Image? : Understanding Graphs with Large Language Models” is out on ArXiv! 🆕
- July 2023 - Our paper on “Balancing the Effect of Training Dataset Distribution of Multiple Styles for Multi-Style Text Transfer” was presented at ACL 2023 Findings.