Mozhi Zhang

mozhi[at]cs.umd.edu

I am a Computer Science Ph.D. student at the University of Maryland and a member of CLIP. My advisor is Jordan Boyd-Graber. I completed my combined B.S. / M.S.E. at the Johns Hopkins University, where I worked with Jason Eisner and David Yarowsky.

I work on natural language processing (NLP) and machine learning (ML). Currently, I focus on improving NLP models with cross-lingual transfer learning and human interaction.

I am visiting New York University in Fall 2019.


Publication

* indicates equal contribution

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

What Can Neural Networks Reason About?
Keyulu Xu, Jingling Li, Mozhi Zhang, Simon S. Du, Ken-ichi Kawarabayashi, Stefanie Jegelka.
Preprint
arxiv bibtex

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