Yuwei Wang   汪 雨薇

PUBLICATION

• Constrained Non-Affine Alignment of Embeddings (ICDM'21)
  Yuwei Wang, Yan Zheng, Yanqing Peng, Michael Yeh, Zhongfang Zhuang, Das Mahashweta, Bendre Mangesh, Feifei Li, Wei Zhang, and Jeff Phillips
  [PDF]
  Embeddings are one of the fundamental building blocks for data analysis tasks. Embeddings are already essential tools for large language models and image analysis, and their use is being extended to many other research domains. The generation of these distributed representations is often a data- and computation-expensive process; yet the holistic analysis and adjustment of them after they have been created is still a developing area. In this paper, we first propose a very general quantitatively measure for the presence of features in the embedding data based on if it can be learned. We then devise a method to remove or alleviate undesired features in the embedding while retaining the essential structure of the data. We use a Domain Adversarial Network (DAN) to generate a non-affine transformation, but we add constraints to ensure the essential structure of the embedding is preserved. Our empirical results demonstrate that the proposed algorithm significantly outperforms the state-of-art unsupervised algorithm on several data sets, including novel applications from the industry.
• 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]
  Modern solutions for implicit discourse relation recognition largely build universal models to classify all of the different types of discourse relations. In contrast to such learning models, we build our model from first principles, analyzing the linguistic properties of the individual top-level Penn Discourse Treebank (PDTB) styled implicit discourse relations: Comparison, Contingency and Expansion. We find semantic characteristics of each relation type and two cohesion devices - topic continuity and attribution - work together to contribute such linguistic properties. We encode those properties as complex features and feed them into a Naive Bayes classifier, bettering baselines (including deep neural network ones) to achieve a new state-of-the-art performance level. Over a strong, feature-based baseline, our system outperforms oneversus-other binary classification by 4.83% for Comparison relation, 3.94% for Contingency and 2.22% for four-way classification.

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