I’m a researcher at the Allen Institute for AI on the Semantic Scholar Research team. Before that, I did some statistics in Seattle and some applied probability at Academia Sinica in Taiwan. I graduated in 2015 with an MS in Statistics from the University of Washington.

Research

I work on NLP over scientific literature, focusing on challenges scientists face with information overload and keeping up-to-date. I’m currently interested in:

• Language modeling for scientific text
• ✨Summarization of scientific papers
• ✨Fact checking claims about scientific phenomena using published literature
• ✨Corpora and resources to support other researchers interested in NLP for scientific text
• ✨Augmented reading of scientific papers to support definitions and note-taking

and I’ve also done some work in:

• Generation
• Explainable AI
• Information extraction
• ✨Science of science

Language modeling

• Don’t Stop Pretraining 🎶: Adapt language models to domains and tasks (ACL 2020) (GitHub) - 🎉 Runner-up for Best Paper
• SciBERT: A pretrained language model for scientific text (EMNLP 2019) (GitHub)

Summarization

• TLDR: Extreme summarization of scientific documents (EMNLP 2020 - Findings) (GitHub)
  • ✨ See live in production on Semantic Scholar
  • In the news: Nature, MIT Tech Review, TNW

Fact checking

• SciFact: Scientific claim verification (EMNLP 2020) (GitHub)
  • ✨ Follow progress on our public leaderboard and live demo
  • In the news: MIT Tech Review, VentureBeat, ZDNet

Corpora and resources

• S2ORC: The Semantic Scholar Open Research Corpus (ACL 2020) (GitHub)
  • ✨ s2orc-doc2json for parsing PDFs and LaTeX to JSON format (GitHub)
• CORD-19: The COVID-19 Open Research Corpus (NLP-COVID at ACL 2020) (OpenReview) (GitHub)
  • SIIRH 2020 at ECIR 2020 keynote (18 min) (April 14, 2020)
  • AWS Education: Research Seminar talk (60 min) (July 29, 2020)
  • In the news: White House OSTP, Science, Nature, TechCrunch, Geekwire [1] [2]

Augmented Reading

• ✨ ScholarPhi: Just-in-Time, Position-Sensitive Definitions of Terms and Symbols (Accepted to CHI 2021)
  • Try our live demo

Generation

• Citation text generation (arXiv 2020; under submission)

Explainable AI

• Explanation-based tuning of opaque machine learners (arXiv 2020; under submission)

Information extraction

• Document-Level definition detection in scholarly documents (SDP at EMNLP 2020)
• Combining distant and direct supervision for neural relation extraction (NAACL 2019)
• Construction of the literature graph in Semantic Scholar (NAACL 2018)

Science of science

• ✨ Text mining approaches for dealing with the rapidly expanding literature on COVID-19 (Briefings in Bioinformatics 2020)
• Quantifying sex bias in clinical trial participation (JAMA 2019)
  • In the news: Quartz article
• Citation count analysis for papers with preprints (arXiv 2018)

Shared tasks

• SciVER at SDP 2021 (NAACL 2021) - Scientific claim verification (link)
• EPIC-QA at TAC 2020 - Open domain question answering challenge: Can systems handle a mixture of questions from experts as well as consumers? (link)
• TREC-COVID at TREC 2020 - Information retrieval challenge over an evolving CORD-19 corpus (link) (JAMIA 2020 paper) (SIGIR Forum 2020 paper)

Workshops

• The 2nd SDP workshop will be at NAACL 2021! Stay tuned! (link)

• 1st SciNLP workshop at AKBC 2020 (link) (recorded talks) - What a success! 166 of 422 AKBC attendees signed up for our workshop! Stay tuned for the next one ;)

My collaborators

All of my projects have been collaborations with other awesome researchers ❤️. Many thanks to:

Waleed Ammar (Google), Iz Beltagy (AI2), Isabel Cachola (JHU), Arman Cohan (AI2), Doug Downey (AI2/Northwestern), Sergey Feldman (AI2), Suchin Gururangan (UW/AI2), Andrew Head (UC Berkeley), Dongyeop Kang (UC Berkeley), Rodney Kinney (AI2), Ben Lee (UW), Ana Marasović (UW/AI2), Mark Neumann (AI2), Swabha Swayamdipta (UW/AI2), Dave Wadden (UW), Lucy Lu Wang (AI2).