Tal Linzen

I am an Assistant Professor of Linguistics and Data Science at New York University. I direct the Computation and Psycholinguistics Lab, which develops computational models of human language comprehension and acquisition, as well as methods for interpreting and evaluating neural network models for natural language processing.

For Fall 2022, I am accepting Ph.D. students through the Data Science program. I also encourage students with relevant interests to apply to the Linguistics program. I especially welcome applications from students who are interested in adult experimental psycholinguistics, in the computational study of human language processing and acquisition, and in how such computational study can contribute to the development of robust and data-efficient artificial intelligence systems. To keep things fair for all applicants, I generally don’t meet with prospective students outside of the admissions process, but I am happy to answer questions not addressed by the Ph.D. program website.

I do not offer internships.

Representative publications

Marten van Schijndel & Tal Linzen (2021). Single-stage prediction models do not explain the magnitude of syntactic disambiguation difficulty. Cognitive Science. [link] [pdf]

Tal Linzen (2020). How can we accelerate progress towards human-like linguistic generalization? ACL. [pdf]

R. Thomas McCoy, Robert Frank & Tal Linzen (2020). Does syntax need to grow on trees? Sources of hierarchical inductive bias in sequence-to-sequence networks. TACL. [arXiv]

Tal Linzen, Emmanuel Dupoux & Yoav Goldberg (2016). Assessing the ability of LSTMs to learn syntax-sensitive dependencies. TACL. [pdf]

Contact

linzen@nyu.edu

Center for Data Science: Office 704
60 5th Avenue
New York, NY 10011
(Office hour: Thursday 10:30-11 am)

Linguistics: Office 514
10 Washington Place
New York, NY 10003
(Office hour: Monday 2-3 pm)

Talks available online

How can we accelerate progress towards human-like linguistic generalization? (ACL position piece; July 2020).

Neural networks as a framework for modeling human syntactic processing (AMLaP keynote; September 2020).

Talk at Allen Institute for Artificial Intelligence (December 2018).