I am a PhD student at New York University studying computer science, focusing on machine learning for natural language. I am jointly advised by Professors Sam Bowman and Kyunghyun Cho, and am part of the Machine Learning for Language group at NYU. I graduated from Harvard University with a bachelor’s in applied mathematics and a master’s in computer science, where I was advised by Alexander Rush and spent time with the Harvard Natural Language Processing group. See my CV, Google Scholar, GitHub for more details. If you need to contact me, send me a message at wangalexc at gmail or on Twitter. If you aren’t sure you have the right Alex Wang, try this directory.
jiant: A Software Toolkit for Research on General-Purpose Text Understanding Models
Yada Pruksachatkun, Phil Yeres, Haokun Liu, Jason Phang, Phu Mon Htut, Alex Wang, Ian Tenney, Samuel R. Bowman
ACL 2020 (demo)
SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems
Alex Wang, Yada Pruksachatkun, Nikita Nangia, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, Samuel R. Bowman
Can You Tell Me How to Get Past Sesame Street? Sentence-Level Pretraining Beyond Language Modeling
Alex Wang, Jan Hula, Patrick Xia, Raghavendra Pappagari, R. Thomas McCoy, Roma Patel, Najoung Kim, Ian Tenney, Yinghui Huang, Katherin Yu, Shuning Jin, Berlin Chen, Benjamin Van Durme, Edouard Grave, Ellie Pavlick, Samuel R. Bowman
Probing What Different NLP Tasks Teach Machines about Function Word Comprehension
Najoung Kim, Roma Patel, Adam Poliak, Alex Wang, Patrick Xia, R. Thomas McCoy, Ian Tenney, Alexis Ross, Tal Linzen, Benjamin Van Durme, Sameul R. Bowman, Ellie Pavlick
StarSem 2019 (Best Paper Award)
What do you learn from context? Probing for sentence structure in contextualized word representations
Ian Tenney, Patrick Xia, Berlin Chen, Alex Wang, Adam Poliak, Benjamin Van Durme, Sam Bowman, Dipanjan Das, Ellie Pavlick
Learning Linguistic Descriptors of User Roles in Online Communities
Alex Wang, William L. Hamilton, Jure Leskovec
NLP+CSS Workshop @ EMNLP 2016
- A Neural Framework for One-Shot Learning: thorough examination in the use of matching networks, a neural network and nonparametric model hybrid, for one-shot learning in various settings. See paper for more details. Completed for my senior thesis, earning high honors.
- Traffic Swarm Optimization: investigation in the use of swarm optimization methods for optimizing traffic light cycles. For more info see this article or this writeup.
- Gaussian Processes for Crime Prediction: an exploration into the use of Gaussian processes to predict future crime rates in cities. See the writeup for details.
- Twitter Plays Chess: crowdsourced chess playing against an AI where users vote for the human team’s next move via Twitter, à la Twitch Plays Pokemon.