Danish Pruthi, PhD Student
https://www.cs.cmu.edu/~ddanish/
Hey! I am Danish Pruthi, and I am a Ph.D candidate in Language Technologies at School of Computer Science in Carnegie Mellon University. I am co-advised by Dr. Graham Neubig and Dr. Zachary C. Lipton. My research goal is to enable machines to understand and explain natural language phenomena. Towards this mission, I work on explaining and interpreting neural representations and models. Prior to this, I worked with Dr. Partha Talukdar at Machine And Language Learning (MALL) Lab in the Indian Institute of Science, Bangalore. I completed my bachelors degree in computer science from BITS Pilani, Pilani in 2015. During my undergraduate years, I had the opportunity to work on some interesting problems at Microsoft Research, India and Google, Hyderabad.
Research Interests: Interpretability, Robustness, NLP
Publications
Explain, Edit, and Understand: Rethinking User Study Design for Evaluating Model Explanations
Siddhant Arora*, Danish Pruthi*, Norman Sadeh, William Cohen, Zachary Lipton, Graham Neubig
Association for the Advancement of Artificial Intelligence (AAAI), 2022Evaluating Explanations: How much do explanations from the teacher aid students?
Danish Pruthi, Rachit Bansal, Bhuwan Dhingra, Livio Baldini Soares, Michael Collins, Zachary Lipton, Graham Neubig, William Cohen
Transactions of the Association for Computational Linguistics (TACL), 2021Do Context-Aware Translation Models Pay the Right Attention?
Kayo Yin, Patrick Fernandes, Danish Pruthi, Aditi Chaudhary, André F. T. Martins, Graham Neubig
Association for Computational Linguistics (ACL), 2021Weakly and Semisupervised Evidence Extraction
Danish Pruthi, Bhuwan Dhingra, Graham Neubig, Zachary Lipton
Findings of EMNLP, 2020Why and when should you pool? Analyzing Pooling in Recurrent Architectures
Pratyush Maini, Keshav Kolluru, Danish Pruthi, Mausam
Findings of EMNLP, 2020NeuSpell: A Neural Spelling Correction Toolkit
Sai Muralidhar Jayanthi, Danish Pruthi, Graham Neubig
EMNLP (Demo Track), 2020Learning to Deceive with Attention-Based Explanations
Danish Pruthi, Mansi Gupta, Bhuwan Dhingra, Graham Neubig, Zachary Lipton
Association for Computational Linguistics (ACL), 2020Combating Adversarial Misspellings with Robust Word Recognition
Danish Pruthi, Bhuwan Dhingra, Zachary Lipton
Association for Computational Linguistics (ACL), 2019SPINE: SParse Interpretable Neural Embeddings
Danish Pruthi*, Anant Subramanian*, Harsh Jhamtani*, Taylor Berg-Kirkpatrick, Eduard Hovy
Association for the Advancement of Artificial Intelligence (AAAI), 2018