Shyam Upadhyay | श्याम उपाध्याय

🗣 /ʃjɑːm ʊ.pɑːd̪ʱ.jɑːj/

I am a Senior Research Scientist working at Google New York on improving the conversational language understanding ability of the Google Assistant. Specifically, I am working on language understanding problems arising at the boundary of speech and text.

Previously, I completed my Ph.D. from the Computer and Information Science Department at the University of Pennsylvania, under the guidance of Dan Roth. My thesis described approaches to exploit cross-lingual representations as a means of extending NLP tools to languages beyond English.

Even before that, I obtained an undergraduate degree in Computer Science and Engineering from the Indian Institute of Technology at Kanpur.

Selected Publications

  1. TIMEDIAL: Temporal Commonsense Reasoning in Dialog
    In ACL 2021
  2. A Dataset for Understanding Disfluencies in Question Answering
    In Findings of ACL 2021
  3. Attention Interpretability across NLP Tasks
    Arxiv Preprint 2019
  4. A General-Purpose Algorithm for Constrained Sequential Inference
    Daniel Deutsch*, Shyam Upadhyay*, and Dan Roth
    In CoNLL 2019
  5. Bootstrapping Transliteration with Constrained Discovery for Low-Resource Languages
    Shyam Upadhyay, Jordan Kodner, and Dan Roth
    In EMNLP 2018
  6. Joint Multilingual Supervision for Cross-lingual Entity Linking
    Shyam Upadhyay, Nitish Gupta, and Dan Roth
    In EMNLP 2018
  7. Looking Beyond the Surface: A Challenge Set for Reading Comprehension over Multiple Sentences
    In NAACL 2018
  8. (Almost) Zero-Shot Cross-Lingual Spoken Language Understanding
    In ICASSP 2018
  9. Beyond Bilingual: Multi-sense Word Embeddings using Multilingual Context
    Shyam Upadhyay, Kai-Wei Chang, Matt Taddy, Adam Kalai, and James Zou
    In Workshop on Repl4NLP 2017
    Best Paper Award
  10. Learning from Explicit and Implicit Supervision Jointly For Algebra Word Problems
    Shyam Upadhyay, Ming-Wei Chang, Kai-Wei Chang, and Wen-tau Yih
    In EMNLP 2016
  11. Cross-lingual Models of Word Embeddings: An Empirical Comparison
    Shyam Upadhyay, Manaal Faruqui, Chris Dyer, and Dan Roth
    In ACL 2016