Me in Montreal in December 2015.

Hi, I’m Jon Gauthier. I’m a Ph.D. student in the Department of Brain and Cognitive Sciences at the Massachusetts Institute of Technology. I build computational models of how people learn, understand, and produce language. I collaborate with members of the Computational Psycholinguistics Laboratory and the Computational Cognitive Science Group, combining methods from artificial intelligence, linguistics, neuroscience, and philosophy. I also co-run the Brain and Cognitive Sciences Philosophy Circle.

Before joining MIT, I did research in natural language processing and machine learning at Stanford University in the Natural Language Processing Group, where I was advised by Christopher Manning. I also spent time as a researcher at OpenAI and Google Brain, where I mainly collaborated with Ilya Sutskever and Oriol Vinyals.

I had the good fortune to begin research at a young age, thanks to the generosity and support of my advisors and academic community. I’m interested in helping ambitious undergraduate students likewise break into the world of academia. Please get in touch!

Recent personal news

Research

(Find me on Google Scholar for an up-to-date list.)

Linking human and artificial neural representations of language.
@InProceedings{gauthier2019linking, author = {Gauthier, Jon and Levy, Roger P.}, title = {Linking human and artificial neural representations of language}, booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing}, month = {November}, year = {2019}, address = {Hong Kong}, publisher = {Association for Computational Linguistics}, }
A rational model of syntactic bootstrapping.
@InProceedings{gauthier2019rational, author = {Gauthier, Jon and Levy, Roger and Tenenbaum, Joshua B.}, title = {A rational model of syntactic bootstrapping}, booktitle = {Proceedings of the 41st Annual Meeting of the Cognitive Science Society}, month = {July}, year = {2019}, address = {Montreal, Canada}, }
Query-guided visual search.
Does the brain represent words? An evaluation of brain decoding studies of language understanding.
@InProceedings{gauthier2018word, author = {Gauthier, Jon and Ivanova, Anna}, title = {Does the brain represent words? An evaluation of brain decoding studies of language understanding.}, booktitle = {Proceedings of the 2nd Conference on Cognitive Computational Neuroscience}, month = {September}, year = {2018}, address = {Philadelphia, Pennsylvania} },
Word learning and the acquisition of syntactic–semantic overhypotheses.
@InProceedings{gauthier2018word, author = {Gauthier, Jon and Levy, Roger and Tenenbaum, Joshua B.}, title = {Word learning and the acquisition of syntactic--semantic overhypotheses}, booktitle = {Proceedings of the 40th Annual Meeting of the Cognitive Science Society}, month = {July}, year = {2018}, address = {Madison, Wisconsin}, }
Are distributional representations ready for the real world? Evaluating word vectors for grounded perceptual meaning.
@misc{1705.11168, Author = {Li Lucy and Jon Gauthier}, Title = {Are distributional representations ready for the real world? Evaluating word vectors for grounded perceptual meaning}, Year = {2017}, Eprint = {arXiv:1705.11168}, }
A paradigm for situated and goal-driven language learning.
@misc{1610.03585, Author = {Jon Gauthier and Igor Mordatch}, Title = {A Paradigm for Situated and Goal-Driven Language Learning}, Year = {2016}, Eprint = {arXiv:1610.03585}, }
A fast unified model for parsing and sentence understanding.
@InProceedings{bowman2016fast, author = {Bowman, Samuel R. and Gauthier, Jon and Rastogi, Abhinav and Gupta, Raghav and Manning, Christopher D. and Potts, Christopher}, title = {A Fast Unified Model for Parsing and Sentence Understanding}, booktitle = {Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, month = {August}, year = {2016}, address = {Berlin, Germany}, publisher = {Association for Computational Linguistics}, pages = {1466--1477}, url = {http://www.aclweb.org/anthology/P16-1139} }
Conditional generative adversarial networks for convolutional face generation.
@TechnicalReport{gauthier2015conditional, author = {Gauthier, Jon}, title = {Conditional generative adversarial networks for convolutional face generation}, year = {2015} }
Exploiting long-distance context in transition-based dependency parsing with recurrent neural networks.

Around the web

Currently reading

Currently reading

The Information: A History, a Theory, a Flood
tagged: mind-tickling and currently-reading
The Haskell Road to Logic, Maths and Programming
tagged: programming, haskell, functional-programming, math, mind-tickling, ...
Learning J
tagged: currently-reading and programming
On LISP: Advanced Techniques for Common LISP
tagged: currently-reading, lisp, and programming