Xuezhe (Max) Ma

Graduate Research Assistant

Language Technologies Institute,

Carnegie Mellon University

5000 Forbes Ave

GHC 5517

Pittsburgh, PA 15213-3891, USA

E-mail: xuezhem at cs.cmu.edu

Carnegie Mellon University

taken on January 14th, 2017

Experiences     Publications    Notes CV    Software

 

 


    

 

Short Intro

I am a fifth-year Ph.D student in Language Technologies Institute at Carnegie Mellon University. I am working with Prof. Eduard Hovy.

Before coming to CMU, I was a master student of Center for Brain-like Computing and Machine Intelligence (BCMI), Shanghai Jiao Tong University, Shanghai, China

I received my Bachelor degree in Computer Science from Shanghai Jiao Tong University, where I was a member of ACM Class, now part of Zhiyuan College in SJTU.

 

My research interests fall in several areas in Machine Learning and Natural Language Processing (NLP), particularly in Structured Prediction, Syntactic and Semantic Parsing, Machine Translation, and Language Generation with Machine Learning and Deep Learning methods.

Recently, I am strongly interested in Deep Generative Models and their applications to NLP and CV tasks.

 

In this year (2019-2020), I am on the academic job market, looking for a faculty position.

 

    

 

Experiences

 

2014.8-present Research Assistant, Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA

Advisor: Prof. Eduard Hovy.

2018.5-2018.8 Full-time Intern, Semantic Scholar Group, Allen Institute for Artificial Intelligence, Seattle, WA, USA.

AI2 Outstanding Intern Award. Mentor: Waleed Amar.

2015.06-2015.08 SCALE2015, Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA

Working on Chinese Entity Discovery and Linking

2012.12-2013.12 Research Assistant, Department of Linguistics, University of Washington, Seattle, WA, USA.

Advisor: Prof. Fei Xia.

2009.7-2009.10 Full-time Intern, Speech Group, Microsoft Research Asia, Beijing, China.

Advisors: Yao Qian and Frank Soong.

2008.7-2012.11 Research Assistant, Center for Brain-like Computing and Machine Intelligence (BCMI), Shanghai Jiao Tong University, Shanghai, China.

Advisors: Prof. Bao-liang Lu and Hai Zhao.

 

    

Publications

[2019]

        Xuezhe Ma, Xiang Kong, Shanghang Zhang and Eduard Hovy
MaCow: Masked Convolutional Generative Flow
Proceddings of Thirty-third Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada. December 2019.
[PDF][arXiv][Bib][code]

        Xuezhe Ma*, Chunting Zhou*, Xian Li, Graham Neubig and Eduard Hovy
FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP 2019), Hong Kong, China. November 2019.
[PDF][arXiv][Bib][code]

        Chunting Zhou, Xuezhe Ma, Junjie Hu and Graham Neubig
Handling Syntactic Divergence in Low-Resource Machine Translation

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP 2019), Hong Kong, China. November 2019.
[PDF][arXiv][Bib][code]

        Xuezhe Ma, Chunting Zhou and Eduard Hovy
MAE: Mutual Posterior-Divergence Regularization for Variational AutoEncoders
Proceedings of 7th International Conference on Learning Representations (ICLR 2019), New Orleans, Louisiana, USA. May 2019.
[PDF][arXiv][Bib][code]

        Zhiting Hu, Haoran Shi, Bowen Tan, Wentao Wang, Zichao Yang, Tiancheng Zhao, Junxian He, Lianhui Qin, Di Wang, Xuezhe Ma, Zhengzhong Liu, Xiaodan Liang, Wangrong Zhu, Devendra Singh Sachan, Eric P. Xing
Texar: A Modularized, Versatile, and Extensible Toolkit for Text Generation

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019) (Best Demo Paper Nomination), Florence, Italy. July 2019.
[PDF][arXiv][Bib][code]

        Zhisong Zhang, Xuezhe Ma and Eduard Hovy
An Empirical Investigation of Structured Output Modeling for Graph-based Neural Dependency Parsing

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019), Florence, Italy. July 2019.
[PDF][arXiv][Bib]

        Yu-Hsiang Lin, Chian-Yu Chen, Jean Lee, Zirui Li, Yuyan Zhang, Mengzhou Xia, Shruti Rijhwani, Junxian He, Zhisong Zhang, Xuezhe Ma, Antonios Anastasopoulos, Patrick Littell and Graham Neubig
Choosing Transfer Languages for Cross-Lingual Learning

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019), Florence, Italy. July 2019.
[PDF][arXiv][Bib]

        Chunting Zhou, Xuezhe Ma, Di Wang and Graham Neubig
Density Matching for Bilingual Word Embedding
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2019), Minneapolis, USA. June 2019.
[PDF][arXiv][Bib][code]

        Wasi Uddin Ahmad*, Zhisong Zhang*, Xuezhe Ma, Eduard Hovy, Kai-Wei Chang and Nanyun Peng
On Difficulties of Cross-Lingual Transfer with Order Differences: A Case Study on Dependency Parsing
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2019), Minneapolis, USA. June 2019.
[PDF][arXiv][Bib]

[2018]

        Xuezhe Ma, Zecong Hu, Jingzhou Liu, Nanyun Peng, Graham Neubig and Eduard Hovy
Stack-Pointer Networks for Dependency Parsing
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL 2018) (Oral), pages 1403-1414, Melbourne, Australia. July 2018.
[PDF][arXiv][Bib][code]

        Xuezhe Ma, Pengcheng Yin, Jingzhou Liu, Graham Neubig and Eduard Hovy
Softmax Q-Distribution Estimation for Structured Prediction: A Theoretical Interpretation for RAML
Arxiv Preprint.
[PDF][arXiv][Bib]

[2017]

        Xuezhe Ma and Eduard Hovy
Neural Probabilistic Model for Non-projective MST Parsing
Proceedings of 5th International Joint Conference on Natural Language Processing (IJCNLP 2017), Taipei, Taiwan. November 2017.
[PDF][arXiv][Bib][code]

        Xuezhe Ma, Yingkai Gao, Zhiting Hu, Yaoliang Yu, Yuntian Deng and Eduard Hovy
Dropout with Expectation-Linear Regularization
Proceedings of 5th International Conference on Learning Representations (ICLR 2017), Toulon, France. April 2017.
[PDF][arXiv][Bib]

        Qizhe Xie, Xuezhe Ma, Zihang Dai and Eduard Hovy
An Interpretable Knowledge Transfer Model for Knowledge Base Completion
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL 2017), Vancouver, Canada. August 2017.
[PDF][arXiv][Bib]

        Xuezhe Ma and Nicolas R Fauceglia, Yiu-Chang Lin and Eduard Hovy
CMU System for Entity Discovery and Linking at TAC-KBP 2017
Proceedings of Text Analytics Conference (TAC 2017).
[PDF][Bib]

[2016]

        Xuezhe Ma and Eduard Hovy
End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL 2016), pages 1064-1074, Berlin, Germany. August 2016.
[PDF][arXiv][Bib][code]

        Zhiting Hu, Xuezhe Ma, Zhengzhong Liu, Eduard Hovy and Eric P. Xing
Harnessing Deep Neural Networks with Logic Rules
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL 2016) (Outstanding Paper Award), pages 2410-2420, Berlin, Germany. August 2016.
[PDF][arXiv][Bib][Supplement]

        Xuezhe Ma, Zhengzhong Liu and Eduard Hovy
Unsupervised Ranking Model for Entity Coreference Resolution
Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2016) (Oral), pages 1012-1018, San Diego, CA, USA. June 2016.
[PDF][arXiv][Bib][code]

        Xuezhe Ma and Nicolas R Fauceglia, Yiu-Chang Lin and Eduard Hovy
CMU System for Entity Discovery and Linking at TAC-KBP 2016
Proceedings of Text Analytics Conference (TAC 2016).
[PDF][Bib]

[2015]

        Xuezhe Ma and Eduard Hovy
Efficient Inner-to-outer Greedy Algorithm for Higher-order Labeled Dependency Parsing
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP 2015), pages 1322-1328, Lisbon, Portugal. September 2015.
[PDF][Bib]

        Nicolas R Fauceglia, Yiu-Chang Lin, Xuezhe Ma and Eduard Hovy
CMU System for Entity Discovery and Linking at TAC-KBP 2015
Proceedings of Text Analytics Conference (TAC 2015).
[PDF][Bib]

        Nicolas R Fauceglia, Yiu-Chang Lin, Xuezhe Ma and Eduard Hovy
Word Sense Disambiguation via PropStore and OntoNotes for Event Mention Detection
Proceedings of the 3rd Workshop on Events: Definition, Detection, Coreference and Representation (NAACL 2015), pages 11-15, Denver, CO, USA. June 2015.
[PDF][Bib]

[2014]

  • Xuezhe Ma and Fei Xia
    Unsupervised Dependency Parsing with Transferring Distribution via Parallel Guidance and Entropy Regularization
    Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL 2014), pages 1337-1348, Baltimore, MA, USA. June 2014.
    [PDF][Bib]

[2013]

  • Xuezhe Ma and Fei Xia
    Dependency Parser Adaptation with Subtrees from Auto-Parsed Target Domain Data
    Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (ACL 2013), pages 585-590, Sofia, Bulgaria. August 2013.
    [PDF][Bib]

[2012]

  • Xuezhe Ma and Hai Zhao
    Fourth-Order Dependency Parsing
    Proceedings of the 24th International Conference on Computational Linguistics (COLING 2012), pages 785-796, Mumbai, India. December 2012.
    [PDF][Bib]
  • Xuezhe Ma and Hai Zhao
    Probabilistic Models for Higher-order Projective Dependency Parsing
    Technical Report: arXiv:1502.04174
    [arXiv][Bib]

[2010]

  • Xuezhe Ma, Xiaotian Zhang, Hai Zhao, Bao-Liang Lu
    Dependency Parser for Chinese Constituent Parsing
    Proceedings of CIPS-SIGHAN-2010, Beijing, China. August, 2010
    [PDF][Bib]
  • Yao Qian, Zhizheng Wu, Xuezhe Ma and Frank Soong
    Automatic Prosody Prediction and Detection with Conditional Random Fields (CRF) Models
    Proceedings of ISCSLP 2010, Tainan, Taiwan. November, 2010.
    [PDF][Bib]

    

Notes

10/36-705: Intermediate Statistics

Software

NeuroNLP2: Deep neural models for core NLP tasks based on Pytorch. [Github]

Implementations of deep neural models for core NLP tasks such as part-of-speech tagging, named entity recognition, dependency parsing, etc.

MaxParser: Graph-based Dependency Parser with Different Orders. [Download]

An implementation of graph-based dependency parser in c++ with algorithms from first order to fourth order.

For more details, please see my paper published in COLING 2012.

 


Top      Experiences      Publications Notes      Software

(Last update: July 10th, 2017)