Harsh Trivedi

email CV Scholar

I am master's student in computer science at Stony Brook University. I work in the Language Understanding and Reasoning Lab and am advised by Professor Niranjan Balasubramanian. My broad interests are Natural Language Processing and Machine Learning. My current research is on Natural Language Inference (Textual Entailment and Question Answering) methods with focus on effective information aggregation.

During my undergraudate studies at DA-IICT, I was advised by Professor Prasenjit Majumder.


  • Deformer: Decomposing Pre-trained Transformers for Faster Question Answering conference
    Qingqing Cao, Harsh Trivedi, Aruna Balasubramanian, Niranjan Balasubramanian
    Association for Computational Linguistics (ACL), 2020
    [paper] [code]
  • Repurposing Entailment for Multi-Hop Question Answering Tasks conference
    Harsh Trivedi, Heeyoung Kwon, Tushar Khot, Ashish Sabharwal, Niranjan Balasubramanian
    North American Chapter of the Association for Computational Linguistics (NAACL), 2019
    [paper] [code] [slides] [bib]
  • Controlling Information Aggregation for Complex Question Answering conference
    Heeyoung Kwon, Harsh Trivedi, Peter Jansen, Mihai Surdeanu, Niranjan Balasubramanian
    European Conference on Information Retrieval (ECIR), 2018
    [paper] [poster] [bib]
  • Noise Correction in Pairwise Document Preferences for Learning to Rank conference
    Harsh Trivedi, Prasenjit Majumder
    Asia Information Retrieval Societies (AIRS), 2016
    [paper] [poster] [bib]
  • Author Masking through Translation workshop
    Yashwant Keswani, Harsh Trivedi, Parth Mehta, Prasenjit Majumder
    Conference and Labs of the Evaluation Forum (CLEF), 2016
    [paper] [poster] [bib]
  • A New Approach to Syllabification of Words in Gujarati conference
    Harsh Trivedi, Aanal Patel, Prasenjit Majumder
    Mining Information & Knowledge Exploration (MIKE), 2015
    [paper] [bib]