Nikita Bhutani

I am currently a PhD candidate in Computer Science and Engineering at the University of Michigan. I am advised by Prof. H. V. Jagadish in the Database Research Group. I am interested in teaching machines how to automatically answer questions asked in natural language in any domain.

Experience

During my graduate studies, I spent two summers at IBM Research in 2016 and 2017, working with Yunyao Li on scalable entity resolution and on-demand curation of text. I was a research intern at Megagon Labs in Summer 2018, working with Wang-Chiew Tan on enriching knowledge bases using conversational question-answer corpora. I received a B.Tech. degree from Indian Institute of Technology, Delhi, and worked as a software engineer for a couple of years before joining the PhD program.

Awards

IBM PhD Scholarship, 2017
UMich PhD Fellowship, 2014

Research

  • NestIE

    Open-domain information extraction for sentences with nested structures

  • Nestique

    Knowledge-based question answering over heterogeneous open knowledge bases

  • LUSTRE

    Learning structured representations of named entities using active learning

  • TextRay

    Hybrid knowledge-based question answering over open and curated knowledge bases

Research Interests

Knowledge base construction, knowledge base modeling, knowledge-based question answering and search, data management, information extraction, and natural language processing

Selected Publications

  • Open Information Extraction from Question-Answer Pairs
    Nikita Bhutani, Yoshihiko Suhara, Wang-Chiew Tan, Alon Halevy, H. V. Jagadish
    Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2019
    PDF
  • Exploiting Structure in Representation of Named Entities using Active Learning
    Nikita Bhutani, Kun Qian, Yunyao Li, H. V. Jagadish, Mauricio A. Hernández, Mitesh Vasa
    27th International Conference on Computational Linguistics (COLING), 2018
  • LUSTRE: An Interactive System for Entity Structured Representation and Variant Generation
    Kun Qian, Nikita Bhutani, Yunyao Li, H. V. Jagadish, Mauricio A. Hernández
    34th IEEE International Conference on Data Engineering (ICDE), 2018
  • Nested propositions in open information extraction
    Nikita Bhutani, H. V. Jagadish, Dragomir Radev
    Conference on Empirical Methods in Natural Language Processing (EMNLP), 2016

Patents

  • Entity Structured Representation and Variant Generation
    Nikita Bhutani, Yunyao Li, Mauricio A. Hernández, Kun Qian, Min Li
    Patent Pending

Working Papers

  • Online Schemaless Querying of Heterogeneous Open Knowledge Bases
    Nikita Bhutani, H. V. Jagadish
    Under Review
  • Hybrid Knowledge-Based Question Answering for Compositional Questions
    Nikita Bhutani, Xinyi Zheng, H. V. Jagadish
    In Submission