Hai Wang
 |
PhD Candidate, |
Short Bio
Since 2014, I have been a PhD student at TTI-Chicago, a philanthropically endowed computer science research institute located in the University of Chicago campus. I am fortunate to work with Prof. David McAllester. I received my Master from Pohang University of Science and Technology (POSTECH) in South Korea, and I got my Bachelor from Wuhan University in China, all in computer science major.
Research
My main research interest lies in unsupervised/weakly supervised natural language processing, with applications in machine reading, machine translation and biomedical data analysis. I also have broad interests in large scale Machine Learning, Deep Learning and Optimization. Particularly, I want to develop theoretically rigorous and practically efficient learning algorithm. I also work on some joint computer vision & NLP problems from time to time.
I gratefully acknowledge the support of Facebook AI Research with a research award supporting my research at TTI-Chicago.
Publications
*-equal contribution
Hai Wang, Dian Yu, Kai Sun, Janshu Chen, Dong Yu, David McAllester and Dan Roth, "Evidence Extraction for Machine Reading Comprehension", CONLL 2019, PDF,Data
Hai Wang, Dian Yu, Kai Sun, Janshu Chen, Dong Yu, "Improving Pre-Trained Multilingual Models with Vocabulary Expansion", CONLL 2019, PDF,Pre-trained Models
Hai Wang, Hoifung Poon, "Deep Probabilistic Logic: A Unifying Framework for Indirect Supervision", EMNLP 2018, PDF,Code
Hai Wang*, Takeshi Onishi*, Kevin Gimpel and David McAllester, "Emergent Predication Structure in Hidden State Vectors of Neural Readers", ACL Workshop 2017 PDF , Best Paper Award
Zewei Chu, Hai Wang, Kevin Gimpel and David McAllester, "Broad Context Language Modeling as Reading Comprehension", EACL 2017, PDF,Training Data
Takaaki Hori, Hai Wang, Chiori Hori, et al, "Dialog State Tracking with Attention-based Sequence-to-Sequence Learning", IEEE SLT 2016, PDF
Takeshi Onishi, Hai Wang, Mohit Bansal, Kevin Gimpel and David McAllester, "Who did What: A Large-Scale Person-Centered Cloze Dataset", EMNLP 2016, PDF,Website
Hai Wang, Mohit Bansal, Kevin Gimpel and David McAllester, "Machine Comprehension with Syntax, Frames, and Semantics", ACL 2015, PDF
Qixing Huang, Hai Wang and Vladlen Koltun, "Single-View Reconstruction via Joint Analysis of Image and Shape Collections", Siggraph 2015, PDF,Code
Siqi Sun*, Hai Wang* and Jinbo Xu, "Inferring Block Structure of Graphical Models in Exponential Families", AISTATS 2015, PDF, Supp
Preprint
Hai Wang, Jason Williams and SingBing Kang, "Learning to Globally Edit Images with Textual Description", Arxiv 2018, PDF,Code
Jialei Wang, Hai Wang and Nathan Srebro, "Reducing Runtime by Recycling Samples", Arxiv 2016, PDF
Industrial Experience
2018.6~2018.9: Interned in Tencent AI Lab, Seattle , with Dong Yu
2017.6~2017.9: Interned in MSR, Redmond , with Hoifung Poon, Chris Quirk and Lucy Vanderwende.
2017.3~2017.6: Interned in MSR, Redmond , work with SingBing Kang and Jason Williams.
2016.4~2016.7: Interned in MERL with Dr. Takaaki Hori.
2011.9~2013.12: Involved in vision research projects from Samsung Electronics.
Courses
Mathematical Foundations, Machine Learning, Algorithm, Learning Theory.
Coding Theory, Approximation Algorithm, Computational Geometry.
Nonlinear Optimization, Convex Optimization, Approximation Theory.
Numerical Analysis, Linear Statistical Model, Graphical Model.
Computer Vision, Natural Language Processing, Pattern Recognition.
Teaching & Service
Introduction to Computer Vision , POSTECH, Spring 2013.
Fundamentals of Deep Learning , UChicago/TTIC, Winter 2017/2018.
Conference Review: EMNLP, ACL, AAAI