Mozhi Zhang

mozhi[at]cs.umd.edu [CV] [Scholar] [Twitter]

I am a fifth-year Ph.D. student at the University of Maryland, advised by Jordan Boyd-Graber. I am currently visiting New York University, hosted by Kyunghyun Cho.

I study natural language processing and machine learning. Currently, I focus on building NLP models with limited training data, using cross-lingual and human-in-the-loop methods.

Previously, I completed my B.S. and M.S.E. at the Johns Hopkins University, where I worked with Jason Eisner and David Yarowsky.

News

New EMNLP paper on improving embeddings with human knowledge
Virtual presentation at ACL on how overfitting helps representation learning
Summer internship at Microsoft Research (LIT group)

Publications

^* = equal contribution

Interactive Refinement of Cross-Lingual Word Embeddings
Michelle Yuan^*, Mozhi Zhang^*, Benjamin Van Durme, Leah Findlater, Jordan Boyd-Graber
EMNLP 2020
arxiv bibtex code

Why Overfitting Isn't Always Bad: Retrofitting Cross-Lingual Word Embeddings to Dictionaries
Mozhi Zhang^*, Yoshinari Fujinuma^*, Michael J. Paul, Jordan Boyd-Graber
ACL 2020
arxiv bibtex code video

What Can Neural Networks Reason About?
Keyulu Xu, Jingling Li, Mozhi Zhang, Simon S. Du, Ken-ichi Kawarabayashi, Stefanie Jegelka
ICLR 2020 (Spotlight)
arxiv bibtex code

Exploiting Cross-Lingual Subword Similarities in Low-Resource Document Classification
Mozhi Zhang, Yoshinari Fujinuma, Jordan Boyd-Graber
AAAI 2020
arxiv bibtex

Are Girls Neko or Shōjo? Cross-Lingual Alignment of Non-Isomorphic Embeddings with Iterative Normalization
Mozhi Zhang, Keyulu Xu, Ken-ichi Kawarabayashi, Stefanie Jegelka, Jordan Boyd-Graber
ACL 2019
arxiv bibtex code