Nelson F. Liu

Nelson Liu
Nelson F. Liu

PhD Student
Computer Science Department
Stanford University

Office: Gates 252
pronouns: he/him

Hi! I'm a first-year PhD student in computer science at Stanford University, where I work in the Natural Language Processing Group.

My research focuses on understanding and augmenting the generalizability and robustness of natural language processing systems. In general, I am interested in bridging the gap between solving individual NLP benchmarks and solving broader NLP tasks. My research is graciously supported by a NSF Graduate Research Fellowship.

Previously, I spent four amazing years as an undergraduate at the University of Washington, where I worked with Noah A. Smith. I've also spent time at the Allen Institute for Artificial Intelligence (AI2) (working with Matt Gardner), and the USC Information Sciences Institute (working with Kevin Knight and Jonathan May).

Thanks to the support of my research mentors, I was fortunate to begin working on research early in my undergraduate career. I’m happy to help ambitious undergraduate students interested in natural language processing or machine learning get started with research—please feel free to email me!

Email: nfliu [strudel] cs.stanford.edu

Links: [Full CV] [Twitter] [Github] [Google Scholar] [Blog]

Recent News

  • (8/2019) Paper on Quoref, a new reading comprehension dataset with questions that require resolving coreference, accepted to EMNLP 2019.
  • (8/2019) I'm participating in the Center for Brains, Minds, and Machines' summer course.
  • (5/2019) New paper on fact-aware language modeling accepted to ACL 2019—congratulations to my amazing collaborators!

Publications

  • Quoref: A Reading Comprehension Dataset with Questions Requiring Coreferential Reasoning
    Pradeep Dasigi, Nelson F. Liu, Ana Marasović, Noah A. Smith, and Matt Gardner.
    In Conference on Empirical Methods in Natural Language Processing & International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), 2019.
    [bib] [abstract] [dataset] [leaderboard]

  • Barack's Wife Hillary: Using Knowledge Graphs for Fact-Aware Language Modeling
    Robert L. Logan IV, Nelson F. Liu, Matthew E. Peters, Matt Gardner, and Sameer Singh.
    In Annual Meeting of the Association for Computational Linguistics (ACL), 2019.
    [bib] [abstract] [poster] [code] [dataset]

  • Linguistic Knowledge and Transferability of Contextual Representations
    Nelson F. Liu, Matt Gardner, Yonatan Belinkov, Matthew E. Peters, and Noah A. Smith.
    In North American Chapter of the Association for Computational Linguistics (NAACL), 2019.
    [bib] [abstract] [slides: pdf, pdf with notes, key] [code]

  • Inoculation by Fine-Tuning: A Method for Analyzing Challenge Datasets
    Nelson F. Liu, Roy Schwartz, and Noah A. Smith.
    In North American Chapter of the Association for Computational Linguistics (NAACL), 2019.
    [bib] [abstract] [slides: pdf, pdf with notes, key] [code]

  • LSTMs Exploit Linguistic Attributes of Data
    Nelson F. Liu, Omer Levy, Roy Schwartz, Chenhao Tan, and Noah A. Smith.
    In ACL Workshop on Representation Learning for NLP (RepL4NLP), 2018. (Best Paper Award).
    [bib] [abstract] [(short) slides] [poster] [code]

  • AllenNLP: A Deep Semantic Natural Language Processing Platform
    Matt Gardner, Joel Grus, Mark Neumann, Oyvind Tafjord, Pradeep Dasigi, Nelson F. Liu, Matthew Peters, Michael Schmitz, and Luke Zettlemoyer.
    In ACL Workshop for Natural Language Processing Open Source Software (NLP-OSS), 2018.
    [bib] [abstract] [code]

  • Discovering Phonesthemes with Sparse Regularization
    Nelson F. Liu, Gina-Anne Levow, and Noah A. Smith.
    In NAACL Workshop on Subword and Character Level Models in NLP (SCLeM), 2018.
    [bib] [abstract] [poster] [code]

  • Crowdsourcing Multiple Choice Science Questions
    Johannes Welbl, Nelson F. Liu, and Matt Gardner.
    In EMNLP Workshop on Noisy User-generated Text, 2017.
    [bib] [abstract] [data] [poster]