Tal Linzen

I am an Assistant Professor of Cognitive Science and Computer Science at Johns Hopkins University, where I direct the JHU Computation and Psycholinguistics Lab. I am also affiliated with the JHU Center for Language and Speech Processing.

In September 2020, I'll be moving to NYU, where I will be Assistant Professor of Linguistics and Data Science.

News

July: We are presenting two papers at CogSci, one on inductive biases through meta-learning and the other on agreement errors in humans and RNNs.

April: The preprint of the review I wrote with Marco Baroni on Syntactic Structure from Deep Learning, for Annual Reviews of Linguistics, is now online.

April: Papers accepted to ACL: cross-linguistic language model syntactic evaluation, data augmentation for robustness to inference heuristics, constituency vs. dependency tree-LSTMs, and an opinion piece on evaluation for 'human-like' linguistic generalization.

Raquel Fernández and I are organizing CoNLL 2020, with a renewed focus on "theoretically, cognitively and scientifically motivated approaches to computational linguistics"!

September: I'll be giving keynote talks at AMLaP 2020 in Potsdam and COLING'2020 in Barcelona.

February: Colloquium talks at UCSD Linguistics (Feb 10) and Data Science (Feb 11).

January: Spoke at the Stanford Linguistics colloquium (Jan 21) and the Berkeley NLP seminar (Jan 23).

January 2020: Paper on the syntactic inductive bias required to learn English question formation accepted to TACL.

November 2019: Paper on syntactic priming for studying neural network representations received honorable mention for the Best Paper Award for Research Inspired by Human Language Learning and Processing at CoNLL.

August 13: Paper on the data efficiency of neural network language models accepted to EMNLP.

August 11: Keynote talk at the Conference on Formal Grammar in Riga.

August 7: Received an NSF award.

July: Yoav Goldberg and I were awarded a grant by the US-Israel Binational Science Foundation.

Contact

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

Representative publications

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. Transactions of the Association for Computational Linguistics. [arXiv]

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.