Xinyi(Cindy) Wang
xinyiw1 <at> cs.cmu.edu

I work on Multilingual Natural Language Processing, focusing on efficient data utilization for low-resource languages, and any other scenarios when the data with desired properties is limited. My goal is to create competitive NLP systems that support speakers of any language variety in the world.

I am currently a research scientist at Google Research working on Multilingual Natural Language Processing. Before that, I did my PhD at the Language Technologies Institute of CMU, working with Graham Neubig. Previously I did my undergrad at University of Notre Dame, where I worked with David Chiang. I was honored to be supported by the Apple Scholars in AI/ML PhD Fellowship.

CV  /  Google Scholar  /  Github

Publication
Expanding Pretrained Models to Thousands More Languages via Lexicon-based Adaptation
Xinyi Wang, Sebastian Ruder, Graham Neubig
ACL, 2022
arxiv  / 
Efficient Test Time Adapter Ensembling for Low-resource Language Varieties
Xinyi Wang, Yulia Tsvetkov, Sebastian Ruder, Graham Neubig
EMNLP Findings, 2021
arxiv  /  slides
Multi-view Subword Regularization
Xinyi Wang, Sebastian Ruder, Graham Neubig
NAACL, 2021
arxiv  /  slides
Meta Back Translation
Hieu Pham*, Xinyi Wang*, Yiming Yang, Graham Neubig
ICLR, 2021
arxiv  /  poster
Balancing Training for Multilingual Neural Machine Translation
Xinyi Wang, Yulia Tsvetkov, Graham Neubig
ACL, 2020
arxiv  /  slides
Optimizing Data Usage via Differentiable Rewards
Xinyi Wang*, Hieu Pham*, Paul Michel, Antonios Anastasopoulos, Graham Neubig, Jaime Carbonell
ICML, 2020
arxiv  /  slides
A Probabilistic Formulation of Unsupervised Text Style Transfer
Junxian He*, Xinyi Wang*, Graham Neubig, Taylor Berg-Kirkpatrick
ICLR, 2020
arxiv  / 
Target Conditioned Sampling: Optimizing Data Selection for Multilingual Neural Machine Translation
Xinyi Wang, Graham Neubig
ACL, 2019
arxiv  /  slides
Multilingual Neural Machine Translation with Soft Decoupled Encoding
Xinyi Wang, Hieu Pham, Philip Arthur, Graham Neubig
ICLR, 2019
arxiv  /  poster
A Tree-based Decoder for Neural Machine Translation
Xinyi Wang, Hieu Pham, Pengcheng Yin, Graham Neubig
EMNLP, 2018
arxiv  /  slides
SwitchOut: an Efficient Data Augmentation Algorithm for Neural Machine Translation
Xinyi Wang*, Hieu Pham*, Zihang Dai, Graham Neubig
EMNLP, 2018
arxiv  /  slides
Growing Better Graphs With Latent-Variable Probabilistic Graph Grammars
Xinyi Wang, Salvador Aguinaga, Tim Weninger, David Chiang
KDD Workshop, 2018
arxiv
XNMT: The extensible neural machine translation toolkit
Graham Neubig, Matthias Sperber, Xinyi Wang, Matthieu Felix, Austin Matthews, Sarguna Padmanabhan, Ye Qi, Devendra Singh Sachan, Philip Arthur, Pierre Godard, John Hewitt, Rachid Riad, Liming Wang
AMTA, 2018
arxiv
Internship

Google Translate, Research Intern hosted by Ankur Bapna, Melvin Johnson, Orhan Firat, Summer 2020

Facebook AI Research, Research Intern hosted by Yacine Jernite, Jason Weston, Michael Auli, Summer 2019

Tsinghua University, Visting Student hosted by Yang Liu, Summer 2017

LinkedIn Inc., Software Engineering Intern, Summer 2016

Google Inc., Engineering Practicum Intern, Summer 2015


The design of this website is borrowed from this guy