Tal Linzen

I am an Assistant Professor in the Department of Cognitive Science at Johns Hopkins University, where I direct the JHU Computational Psycholinguistics Lab.

I am also affiliated with the Center for Language and Speech Processing.

Representative publications

Tal Linzen (2019). What can linguistics and deep learning contribute to each other? Response to Pater. Language 95(1), e98–e108. [link] [pdf]

Tal Linzen & Florian Jaeger (2016). Uncertainty and expectation in sentence processing: Evidence from subcategorization distributions. Cognitive Science 40(6), 1382–1411. [link] [pdf] [bib]

Tal Linzen, Emmanuel Dupoux & Yoav Goldberg (2016). Assessing the ability of LSTMs to learn syntax-sensitive dependencies. Transactions of the Association for Computational Linguistics 4, 521–535. [link] [pdf] [bib]

Here's a video of a talk I gave in December 2018 at the Allen Institute for Artificial Intelligence.

Short bio

Before joining JHU, I was a postdoctoral researcher in LSCP and IJN in the Cognitive Science Department at the École Normale Supérieure in Paris, where I worked with Emmanuel Dupoux and Benjamin Spector.

I obtained my Ph.D. in Linguistics in September 2015 from New York University, under the supervision of Alec Marantz. During my Ph.D., I also collaborated with Gillian Gallagher, Maria Gouskova and Liina Pylkkänen at NYU, as well as with Florian Jaeger at the University of Rochester.

Before that, I obtained a B.Sc. in Mathematics and Linguistics and an M.A. in Linguistics (with Mira Ariel), both from Tel Aviv University, and worked as a data scientist and software engineer.

Contact

tal.linzen@jhu.edu
243 Krieger Hall
Cognitive Science Department
Johns Hopkins University
3400 N. Charles Street
Baltimore, MD 21218

News

May 3: Upcoming keynote talk at Midwest Speech and Language Days.

April 24: Upcoming talk at the Cognitive Talk Series at Princeton.

April 18: Upcoming talk at the CompLang seminar at MIT.

March 13: I received a Google Faculty Research Award.

February 22: Paper with Shauli Ravfogel and Yoav Goldberg accepted to NAACL.

February 8: LTI colloquium talk at Carnegie Mellon University.

December: Paper on interpreting neural network internal representations using tensor products accepted to ICLR.

Winter break talks: Yale Linguistics (Dec 10), Microsoft Research Redmond (Dec 13), Allen AI Institute (Dec 14), Google New York (Jan 7).

November: paper and extended abstract accepted to the Society for Computation in Linguistics.

November 1: Co-organized the workshop on analyzing and interpreting neural networks for NLP (at EMNLP).