Y
Yue Zhang
Researcher at Westlake University
Publications - 303
Citations - 11890
Yue Zhang is an academic researcher from Westlake University. The author has contributed to research in topics: Parsing & Dependency grammar. The author has an hindex of 50, co-authored 294 publications receiving 9107 citations. Previous affiliations of Yue Zhang include Microsoft & National University of Singapore.
Papers
More filters
Proceedings Article
Deep learning for event-driven stock prediction
TL;DR: This work proposes a deep learning method for event-driven stock market prediction that can achieve nearly 6% improvements on S&P 500 index prediction and individual stock prediction, respectively, compared to state-of-the-art baseline methods.
Proceedings Article
Transition-based Dependency Parsing with Rich Non-local Features
Yue Zhang,Joakim Nivre +1 more
TL;DR: This paper shows that it can improve the accuracy of transition-based dependency parsers by considering even richer feature sets than those employed in previous systems by improving the accuracy in the standard Penn Treebank setup and rivaling the best results overall.
Proceedings ArticleDOI
Chinese NER Using Lattice LSTM
Yue Zhang,Jie Yang +1 more
TL;DR: The authors proposed a lattice-structured LSTM model for Chinese NER, which encodes a sequence of input characters as well as all potential words that match a lexicon.
Proceedings Article
Target-dependent twitter sentiment classification with rich automatic features
Duy Tin Vo,Yue Zhang +1 more
TL;DR: This paper shows that competitive results can be achieved without the use of syntax, by extracting a rich set of automatic features from a tweet, using distributed word representations and neural pooling functions to extract features.
Proceedings ArticleDOI
A tale of two parsers: investigating and combining graph-based and transition-based dependency parsing using beam-search
Yue Zhang,Stephen Clark +1 more
TL;DR: This paper proposed a beam-search-based parser that combines both graph-based and transition-based parsing into a single system for training and decoding, showing that it outperforms both the pure graphbased and the pure transition based parsers.