Y
Yue Wang
Researcher at University of North Carolina at Chapel Hill
Publications - 52
Citations - 1159
Yue Wang is an academic researcher from University of North Carolina at Chapel Hill. The author has contributed to research in topics: Computer science & Task (project management). The author has an hindex of 14, co-authored 43 publications receiving 729 citations. Previous affiliations of Yue Wang include Shanghai Jiao Tong University & Microsoft.
Papers
More filters
Proceedings ArticleDOI
A Novel Cascade Binary Tagging Framework for Relational Triple Extraction
TL;DR: The authors proposed a cascade binary tagging framework (CasRel) derived from a principled problem formulation, which models relations as functions that map subjects to objects in a sentence, which naturally handles the overlapping problem.
Posted Content
A Novel Cascade Binary Tagging Framework for Relational Triple Extraction
TL;DR: A fresh perspective to revisit the relational triple extraction task is introduced and a novel cascade binary tagging framework (CasRel) derived from a principled problem formulation is proposed, which naturally handles the overlapping problem.
Proceedings Article
The Genia Event Extraction Shared Task, 2013 Edition - Overview
TL;DR: The Genia Event Extraction task is organized for the third time, in BioNLP Shared Task 2013, and the task is modified in a number of points towards knowledge based construction.
Journal ArticleDOI
The Genia Event and Protein Coreference tasks of the BioNLP Shared Task 2011.
Jin-Dong Kim,Ngan Luu-Thuy Nguyen,Yue Wang,Jun'ichi Tsujii,Toshihisa Takagi,Akinori Yonezawa +5 more
TL;DR: The Genia task aimed to measure the progress of the community since 2009, and to evaluate generalization of the technology to full text papers, and showed that the coreference resolution performance in biomedical domain is lagging behind that in newswire domain.
Proceedings ArticleDOI
Beyond Ranking: Optimizing Whole-Page Presentation
TL;DR: A novel framework that learns the optimal page presentation to render heterogeneous results onto search result page (SERP) and can learn its own result presentation strategy purely from data, without even knowing the "probability ranking principle".