Timothy Dozat
I joined Google as a research scientist in January 2019. My current work falls into two broad categories: neural network architectures (and some of the theory behind them), emphasizing language model pretraining and distillation; and "classic" NLP tasks, such as part-of-speech tagging and parsing. I've also recently been collaborating with teams working on the Google Assistant. I received my PhD in Lingustics from Stanford University, where I worked under Chris Manning on developing Universal Dependencies and building neural parsers that could reproduce it. I also dabbled in convex optimization at one point, and I might come back to it someday.
Research Areas
Authored Publications
Sort By
Google
FormNetV2: Inductive Multimodal Graph Contrastive Learning for Form Document Information Extraction
Chun-Liang Li
Hao Zhang
Xiang Zhang
Kihyuk Sohn
Nikolai Glushnev
Joshua Ainslie
Nan Hua
ACL (2023)
Dialect-robust Evaluation of Generated Text
Jiao Sun
Elizabeth Clark
Sebastian Gehrmann
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Association for Computational Linguistics, Toronto, Canada (2023), pp. 6010-6028
FRMT: A Benchmark for Few-Shot Region-Aware Machine Translation
Jan A. Botha
Xavier Garcia
Transactions of the Association for Computational Linguistics (2023)
FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information Extraction
Chun-Liang Li
Nan Hua
Joshua Ainslie
Association for Computational Linguistics (ACL) (2022)
