Eunsol Choi

a Ph.D student in CSE at the University of Washington

profile Seattle, Washington
Google Scholar


I study natural language processing, focusing on extracting and querying information about entities from text. More broadly, my research covers machine learning and computational social science. My advisors at the UW are Luke Zettlemoyer and Yejin Choi. Prior to UW, I worked with Lillian Lee at Cornell.



  • FlowQA: Grasping Flow in History For Conversational Machine Comprehension
  • pair2vec: Compositional Word-Pair Embeddings for Cross-Sentence Inference
  • Publications (* equal contribution)

  • Neural Metaphor Detection in Context EMNLP 18 short
  • QuAC : Question Answering in Context EMNLP 18 long
  • Ultra-Fine Entity Typing ACL 18 long
  • Truth of Varying Shades: Analyzing Language in Fake News and Political Fact-Checking EMNLP 17 short
  • Zero-Shot Relation Extraction Via Reading Comprehension CoNLL 17 long
  • Coarse-to-Fine Question Answering for Long Documents ACL 17 long
  • TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension ACL 17 long
  • Document-level Sentiment Inference with Social, Faction, and Discourse Context ACL 16 long

      Eunsol Choi, Hannah Rashkin, Yejin Choi and Luke Zettlemoyer


  • Extracting Structured Scholarly Information from Machine Translation Literature LREC 16 long

      Eunsol Choi*, Matic Horvat *, Jonathan May, Kevin Knight, Daniel Marcu


  • Scalable Semantic Parsing With Partial Ontologies ACL 15 long
  • Scaling Semantic Parsers with On-the-Fly Ontology Matching EMNLP 13 long
  • Hedge detection as a lense on framing in the GMO debates: A position paper ACL 12 workshop
  • ETC

    How to pronounce 'Eunsol'?
    Korean version: [] Easier version: []
    My name means soft, persistent love in ancient Korean.