About
I am research scientist at Microsoft in Seattle, where I work on NLP technologies.
In June 2021 I graduated with a PhD in Computer Science from Stanford University,
advised by Dan Jurafsky in the Natural Language Processing Group.
Before Stanford, I studied Computer Science and Biology at Williams College.
Feel free to send me an email if you want to reach out.
Last updated 6/11/21 -- please see my Google Scholar for a complete list of publications.
Research
|
Causal Effects of Linguistic Properties
Reid Pryzant, Dallas Card, Dan Jurafsky, Victor Veitch, Dhanya Sridhar
NAACL, 2021 (code)
|
|
Automatically Neutralizing Subjective Bias in Text
Reid Pryzant, Richard Diehl Martinez, Nathan Dass,
Sadao Kurohashi, Dan Jurafsky, Diyi Yang
AAAI, 2020 (code)
|
|
Interpretable Neural Architectures for Attributing an Ad's Performance to its Writing Style
Reid Pryzant, Sugato Basu, Kazoo Sone
EMNLP -- BlackboxNLP, 2018 (code)
|
|
Deconfounded Lexicon Induction for Interpretable Social Science
Reid Pryzant, Kelly Shen, Dan Jurafsky, Stefan Wager
NAACL, 2018 (code, project homepage, blogpost)
|
|
JESC: Japanese-English Subtitle Corpus
Reid Pryzant, Denny Britz, Young-joo Chung, Dan Jurafsky
LREC, 2018 (dataset homepage)
|
|
Predicting Sales from the Language of Product Descriptions
Reid Pryzant, Young-joo Chung, Dan Jurafsky
SIGIR -- eCom, 2017 (Stanford news article on this)
|
|
Effective Domain Mixing for Neural Machine Translation
Denny Britz, Quoc Le, Reid Pryzant
EMNLP -- WMT, 2017
|
|
Monitoring Ethiopian Wheat Fungus with Satellite Imagery and Deep Feature Learning
Reid Pryzant, Stefano Ermon, David Lobell
CVPR -- EarthVision, 2017 (best presentation award)
|
|
The Prochlorococcus Carbon Dioxide-Concentrating Mechanism
Claire Ting, Kate Dusenbury, Reid Pryzant, et al.
Photosynthesis Research, 2015
|
|
The Prochlorococcus Carboxysome: Links to Ecotype Differentiation
Claire Ting, Reid Pryzant.
American Society for Microbiology Meeting, 2014
|
Code
|
Causal Attribution
Open-source toolkit for finding text features which are most predictive of outcomes while controlling for confounds.
[Blogpost]
|
|
Style Transfer
Pytorch implementation of the Delete, Retrieve, Generate style transfer algorithm.
|
|
Measuring Data Domain Similarity
Code for computing Proxy A-Distance (PAD) between two domain distributions.
|
|
NMT (2017)
State-of-the-art neural machine translation system
|
|
Reinforcement Learning Algorithms
Open-source reinforcement learning algorithms and Atari Breakout emulator.
[Poster] [Paper]
|
Data
|
Wikipedia Neutrality Corpus (WNC)
Parallel corpus of biased and unbiased sentences harvested from Wikipedia.
|
|
Japanese-English Subtitle Corpus (JESC)
Parallel corpus of aligned Japanese/English tv and movie subtltles.
|
