Yuan Zhang

Research Sientist, Google
Email: zhangyua at google com

---

Research

I got my PhD degree on Jan 2017. My research advisor is Prof. Regina Barzilay. I am currently a research scientist at Google.

Before coming to MIT, I was an undergraduate at Tsinghua University, working with Prof. Jie Tang.

I interned at Google NLP Parsing Team during the summer 2015, working with David Weiss and Slav Petrov.

My CV is here

---

Publications

• Transfer Learning for Low-resource Natural Language Analysis
  Yuan Zhang
  PhD Thesis, 2017.
  [pdf, slides]
  

• Aspect-augmented Adversarial Networks for Domain Adaptation
  Yuan Zhang, Regina Barzilay, Tommi Jaakkola
  Preprint.
  [pdf, code]
  

• Stack-propagation: Improved Representation Learning for Syntax
  Yuan Zhang, David Weiss
  In proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), 2016.
  [pdf, slides]
  

• Ten Pairs to Tag - Multilingual POS Tagging via Coarse Mapping between Embeddings
  Yuan Zhang, David Gaddy, Regina Barzilay, Tommi Jaakkola
  In proceedings of North American Chapter of the ACL (NAACL), 2016.
  [pdf, slides, code]
  

• Hierarchical Low-Rank Tensors for Multilingual Transfer Parsing
  Yuan Zhang, Regina Barzilay
  In proceedings of Empirical Methods in Natural Language Processing (EMNLP), 2015.
  [pdf, poster, code]
  

• Randomized Greedy Inference for Joint Segmentation, POS Tagging and Dependency Parsing
  Yuan Zhang, Chengtao Li, Regina Barzilay, Kareem Darwish
  In proceedings of North American Chapter of the ACL (NAACL), 2015.
  [pdf, slides, code]
  

• High-Order Low-Rank Tensors for Semantic Role Labeling
  Tao Lei, Yuan Zhang, Regina Barzilay, Lluís Màrquez, Alessandro Moschitti
  In proceedings of North American Chapter of the ACL (NAACL), 2015.
  [pdf, slides, code]
  

• Greed is Good if Randomized: New Inference for Dependency Parsing
  Yuan Zhang*, Tao Lei*, Regina Barzilay, Tommi Jaakkola (*: Equal contribution)
  In proceedings of Empirical Methods in Natural Language Processing (EMNLP), 2014.
  [pdf, slides, code]
  

• Steps to Excellence: Simple Inference with Refined Scoring of Dependency Trees
  Yuan Zhang, Tao Lei, Regina Barzilay, Tommi Jaakkola Amir Globerson
  In proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), 2014.
  [pdf, slides, code]
  Note: Marco Kuhlmann pointed out an issue in our Random Walk-based sampling algorithm. Here is the updated version: pdf, code.

• Low-Rank Tensors for Scoring Dependency Structures
  Tao Lei, Yu Xin, Yuan Zhang, Regina Barzilay, Tommi Jaakkola
  In proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), 2014.
  Best Student Paper Award
  [pdf, slides, code]

• Parsing with Sparse Annotated Resources
  Yuan Zhang,
  Master Thesis, 2013.
  [pdf]

• Transfer Learning for Constituency-Based Grammars
  Yuan Zhang, Regina Barzilay, Amir Globerson
  In proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), 2013.
  [pdf, code]

• Learning to Map into a Universal POS Tagset
  Yuan Zhang, Roi Reichart, Regina Barzilay, Amir Globerson
  In proceedings of Empirical Methods in Natural Language Processing (EMNLP), 2012.
  [pdf, code & data]

Older publications:

• Quantitative Study of Individual Emotional States in Social Networks
  Jie Tang, Yuan Zhang, Jimeng Sun, Jinghai Rao, Wenjing Yu, Yiran Chen, and ACM Fong
  IEEE Transactions on Affective Computing (TAC), 2012.
  [pdf]

• MoodCast: Emotion Prediction via Dynamic Continuous Factor Graph Model
  Yuan Zhang, Jie Tang, Jimeng Sun, Yiran Chen, and Jinghai Rao
  In Proceedings of 2010 IEEE International Conference on Data Mining (ICDM), 2010.
  [pdf]

• MQuery: Fast Graph Query via Semantic Indexing for Mobile Context
  Yuan Zhang, Ning Zhang, Jie Tang, Jinghai Rao, Wenbin Tang
  In Proceedings of 2010 IEEE/WIC/ACM International Conferences on Web Intelligence (WI), 2010.
  [pdf]

---