Tal Linzen

I am an Assistant Professor of Linguistics and Data Science at New York University, and a Research Scientist at Google. At NYU, I direct the Computation and Psycholinguistics Lab; we use behavioral experiments and computational methods to study how people learn and understand language. We also develop methods for evaluating, understanding and improving computational systems for language processing.

For inquiries about DS-1011, Natural Language Processing with Representation Learning, in Fall 2022: Here is the syllabus for a previous version of the class. This class will open to students who are not enrolled in the Master's program in Data Science in August 2022; we will not handle requests for permission to enroll until then.

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]



Center for Data Science: Office 704
60 5th Avenue
New York, NY 10011

Linguistics: Office 514
10 Washington Place
New York, NY 10003

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).