ABOUT
Hi! I'm a second-year Ph.D. student at University of Utah, advised by Prof. Feifei Li. I received my B.S. degree in Computer Science from East China Normal University.
Previously, I was a research intern at Visa Research, working with Yan Zheng and Wei Zhang; a visiting student at UC Berkeley, working with Min Du and Prof. Dawn Song; a research and development intern at Alibaba, working with Tieying Zhang.
My research interests focus on machine learning for natural language processing, data mining, and data management. As a quick learner, I'm also passionate about exploring new fields!
EDUCATION
- 2019.01 - NOW | Ph.D. @ Computer Science, University of Utah
- 2017.08 - 2018.12 | M.S. @ Computer Science, University of Utah
- 2013.09 - 2017.06 | B.S. @ Computer Science, East China Normal University
- 2014.09 - 2015.02 | Exchange student @ Computer Science, Shanghai Jiao Tong University
RESEARCH EXPERIENCE
- 2017.08 - NOW | Research Assistant @ University of Utah, InitialD Lab
- 2019.05 - 2019.08 | Research Intern @ Visa Research, Data Analytics and Fraud Detection
- 2019.01 - 2019.05 | Visiting Student @ University of California, Berkeley
- 2018.05 - 2018.08 | R&D Intern @ Alibaba Inc, Intelligent Database
PUBLICATION
- Feature Detection and Attenuation in Embeddings (arXiv:1910.05862)
Yuwei Wang, Yan Zheng, Yanqing Peng, Wei Zhang, Feifei Li
[PDF]
We first propose an innovative embedding analyzing method that quantitatively measures the features in the embedding data. Then we propose an unsupervised method to remove or alleviate undesired features in the embedding by applying Domain Adversarial Network (DAN). Our empirical results demonstrate that the proposed algorithm has good performance on both industry and natural language processing benchmark datasets. - Linguistic Properties Matter for Implicit Discourse Relation Recognition:Combining Semantic Interaction, Topic Continuity and Attribution (AAAI'18 ORAL)
Wenqiang Lei, Yuanxin Xiang, Yuwei Wang, Qian Zhong, Meichun Liu, Min-Yen Kan
[PDF]
We demonstrate the cooperation of discourse relations’ semantic characteristics and the two cohesion devices of topic continuity and attribution. By encoding those patterns as complex features, we obtain significant improvement over a strong baseline, achieving a new state-of-the-art level of performance.
HONORS
PROGRAMMING CONTEST
- Lucid Programming Competition, 2017
Runner-up - Microsoft MSFT3c Coding Competition, 2017
Runner-up - National Olympiad in Informatics (NOIp), 2013
First Prize
SCHOLARSHIPS
- Grace Hopper Conference Scholarship (full reimbursement), 2018
AnitaB.org - Excellent Bachelor Thesis Award, 2017
East China Normal University - ECNU Scholarship - First Class, 2014, 2015, 2016
East China Normal University
Services
REVIEWER
- Main Conferences: DASFAA2020