I am an Assistant Professor at the Mehta Family School of Data Science & Artificial Intelligence, Department of Data Science, Indian Institute of Technology (IIT) Palakkad.

My research focuses on natural language processing (NLP).

Previously, I was a postdoc in the Computer Science department at the University of Victoria, where I worked with Neil Ernst. I was a scientist at TCS Research. I have also spent time at LILY Lab at the Department of Computer Science, Yale University, as a TATA Visiting Scholar.

I completed my master’s degree and PhD in Computer Science and Engineering at IIT Madras, under the guidance of Sutanu Chakraborti.

My first language (L1) is Marathi (मराठी). Devanagari script is used for writing Marathi texts. In Devanagari, my name is written as स्वप्निल हिंगमिरे.

Research Questions

The following are some questions that drive my research.

1. How can we measure the quality of output produced by an NLP system?
2. How can we ensure that what we are measuring is truly what we want to measure?
3. What are the axioms of an evaluation metric? How can we assess their ecological validity?
4. Which heuristics and biases do we use when interpreting a text? How can we model them computationally?
5. What makes an interpretation subjective or objective?
6. How can we evaluate interpretability? What are the factors that influence interpretation?
7. How can we develop a user model of a linguistic phenomenon (e.g., processing metaphors)? What kind of linguistic knowledge will be necessary for these user and computational models? Will such knowledge reduce the amount of training data needed? (especially in low-resource settings)

Selected Publications

Objectifying the Subjective: Cognitive Biases in Topic Interpretations
Swapnil Hingmire, Ze Shi Li, Shiyu (Vivienne)Zeng, Ahmed Musa Awon, Luiz Franciscatto Guerra, Neil Ernst
TACL 2025 (accepted for publication)

R-VGAE: Relational-variational Graph Autoencoder for Unsupervised Prerequisite Chain Learning
Irene Li, Alexander R. Fabbri, Swapnil Hingmire, Dragomir R. Radev
COLING 2020

Identification of Alias Links among Participants in Narratives
Sangameshwar Patil⁺, Sachin Pawar⁺, Swapnil Hingmire⁺, Girish Keshav Palshikar, Vasudeva Varma, Pushpak Bhattacharyya
ACL 2018 (⁺ Equal contribution)

Measuring Topic Coherence through Optimal Word Buckets
Nitin Ramrakhiyani, Sachin Pawar, Swapnil Hingmire, Girish Keshav Palshikar
EACL 2017

WikiLDA: Towards More Effective Knowledge Acquisition in Topic Models using Wikipedia
Swapnil Hingmire, Sutanu Chakraborti, Girish Keshav Palshikar, Abhay Sodani
K-CAP 2017

Sprinkling Topics for Weakly Supervised Text Classification
Swapnil Hingmire, Sutanu Chakraborti
ACL 2014

Topic Labeled Text Classification: a Weakly Supervised Approach
Swapnil Hingmire, Sutanu Chakraborti
SIGIR 2014

Document Classification by Topic Labeling
Swapnil Hingmire, Sandeep Chougule, Girish K. Palshikar, Sutanu Chakraborti
SIGIR 2013

Full list of publications

Teaching

AI Ethics (jointly with Garima Shakya): Jan-May 2025

Machine Learning: Aug-Dec 2025, Aug-Dec 2024

Natural Language Processing: Jan-May 2025, Jan-May 2022

Research Group

Current
MS: G. L. John Salvin
PhD: Gollapalli Babblu
MTech: Abigairl Nyasha Chigwededza, Budde Shrikant Tryambak, Sudhin S

Past
MTech: Ontiwell Khongthaw

---

Template by Maria Antoniak