Dinghan Shen

I am Dinghan Shen, a fourth-year Ph.D. student in machine learning at Duke University, and I am affiliated with Information Initiative at Duke (iiD). My advisor is Professor Lawrence Carin. Before coming to Duke, I earned my B.Eng. degree at Peking University in 2015.

My Ph.D. research interests focus on the intersection of deep learning and natural language processing, and I am particularly interested in:

(1) natural language reasoning and understanding tasks;

(2) long-form text generation.

I can be reached at: dinghan.shen@duke.edu.

[Google Scholar] [Linkedin] [Github]

Publications

1. Liqun Chen, Yizhe Zhang, Ruiyi Zhang, Chenyang Tao, Zhe Gan, Haichao Zhang, Bai Li, Dinghan Shen, Changyou Chen, Lawrence Carin, Improving Sequence-to-Sequence Learning via Optimal Transport, Seventh International Conference on Learning Representations (ICLR 2019).


2. Dinghan Shen, Xinyuan Zhang, Ricardo Henao and Lawrence Carin, Improved Semantic-Aware Network Embedding with Fine-Grained Word Alignment, Conference on Empirical Methods in Natural Language Processing (EMNLP 2018). Oral presentation

3. Dinghan Shen, Martin Renqiang Min, Yitong Li and Lawrence Carin, Learning Context-Sensitive Convolutional Filters for Text Processing, Conference on Empirical Methods in Natural Language Processing (EMNLP 2018). Oral presentation


4. Xinyuan Zhang, Yitong Li, Dinghan Shen and Lawrence Carin, Diffusion Maps for Textual Network Embedding, Neural Information Processing Systems (NeurIPS 2018). Spotlight


5. Liqun Chen, Shuyang Dai, Chenyang Tao, Dinghan Shen, Zhe Gan, Haichao Zhang, Yizhe Zhang and Lawrence Carin, Adversarial Text Generation via Feature-Mover's Distance, Neural Information Processing Systems (NeurIPS 2018).


6. Pengyu Cheng, Chang Liu, Chunyuan Li, Dinghan Shen, Ricardo Henao and Lawrence Carin, Straight-Through Estimator as Projected Wasserstein Gradient Flow, Workshop on Bayesian Deep Learning (NeurIPS 2018).


7. Xin Wang, Qiuyuan Huang, Asli Celikyilmaz, Jianfeng Gao, Dinghan Shen, Yuan-Fang Wang, William Yang Wang, Lei Zhang, Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation, Unpublished manuscript. 2018.


8. Ruiyi Zhang, Changyou Chen, Zhe Gan, Wenlin Wang, Liqun Chen, Dinghan Shen, Guoyin Wang, Lawrence Carin, Sequence Generation with Guider Network, Unpublished manuscript. 2018.


9. Dinghan Shen, Qinliang Su, Paidamoyo Chapfuwa, Wenlin Wang, Guoyin Wang, Ricardo Henao and Lawrence Carin, NASH: Toward End-to-End Neural Architecture for Generative Semantic Hashing, Association for Computational Linguistics 2018 Conference (ACL 2018). Best Long Paper Award, Honorable Mention: 6/1018, 0.6% [Link]


10. Dinghan Shen, Guoyin Wang, Wenlin Wang, , Martin Renqiang Min, Qinliang Su, Yizhe Zhang, Chunyuan Li, Ricardo Henao and Lawrence Carin, Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms , Association for Computational Linguistics 2018 Conference (ACL 2018). [Code]


11. Guoyin Wang, Chunyuan Li, Wenlin Wang, Yizhe Zhang, Dinghan Shen, Xinyuan Zhang, Ricardo Henao and Lawrence Carin, Joint Embedding of Words and Labels for Text Classification, Association for Computational Linguistics 2018 Conference (ACL 2018). [Code]


12. Wenlin Wang, Zhe Gan, Wenqi Wang, Dinghan Shen, Jiaji Huang, Wei Ping, Sanjeev Satheesh, Lawrence Carin, Topic Compositional Neural Language Model, International Conference on Artificial Intelligence and Statistics (AISTATS 2018).


13. Dinghan Shen, Yizhe Zhang, Ricardo Henao, Qinliang Su, Lawrence Carin, Deconvolutional Latent-Variable Model for Text Sequence Matching, Proc. American Association of Artificial Intelligence (AAAI 2018). Oral presentation


14. Yitong Li, Martin Renqiang Min, Dinghan Shen, David Carlson, Lawrence Carin, Video Generation from Text, Proc. American Association of Artificial Intelligence (AAAI 2018).


15. Yizhe Zhang, Dinghan Shen, Guoyin Wang, Zhe Gan, Ricardo Henao, and Lawrence Carin, Deconvolutional Paragraph Representation Learning, Neural Information Processing Systems (NIPS 2017). [Code]


16. Yizhe Zhang, Zhe Gan, Kai Fan, Zhi Chen, Ricardo Henao, Dinghan Shen, and Lawrence Carin, Adversarial Feature Matching for Text Generation, International Conference on Machine Learning (ICML 2017). [Code]

Education

  • Aug. 2015 - present, Department of Electrical & Computer Engineering, Duke University

Advisor: Prof. Lawrence Carin

  • Sep. 2011 - May 2015, College of Engineering, Peking University
  • May 2013 - Aug. 2013, Exchange student, University of California, Berkeley

Experience

  • Jan 2019 - May 2019, Research Intern, Language Team, Google AI (NYC)

Mentors: Dipanjan Das, Ankur Parikh

  • May 2018 - Aug. 2018, Research Intern, MSR AI, Microsoft Research (Redmond)

Mentors: Asli Celikyilmaz, Jianfeng Gao

  • May 2017 - Aug. 2017, Research Intern, Machine Learning Group, NEC Labs America (Princeton)

Mentor: Martin Renqiang Min

Honors & Awards

Best Long Paper Award, Honorable Mention (6/1018, 0.6%), ACL 2018 (Melbourne, Australia)

Pratt Engineering School Fellowship, Duke University (2015 - 2016)

Outstanding Undergraduate Dissertation Award, Peking University, May 2015 (ranked top 2/114 in the department)

Merit student, Peking University, Oct. 2014 (ranked top 5/114 in the department)

Suzhou Industrial Park Scholarship, Peking University, Oct. 2014

First Prize, Chinese National Mathematical Olympic Contest, Sep. 2010

Graduate Coursework

Computer Science: Machine Learning (STA 561), Advanced Machine Learning (STA 571), Bayesian and Modern Statistics (STA 601), Textual Data Acquisition & Analysis (ECE 590), Statistical Computation (STA 663), Programming, Data Structures and Algorithms in C++ (ECE 551), Reinforcement Learning (COMPSCI 590), Probability for Electrical and Computer Engineers (ECE 555)

Business/Entrepreneurship: Finance in High-Tech Industries (EGRMGMT 530), Management in High-Tech Industries (EGRMGMT 540)