My research interest includes machine learning based natural language processing, web information extraction and financial market prediction. For natural language processing, I work on natural language parsing and generation (in particular for English and Chinese), as well as machine translation. I also work on other applications of machine learning, such as Kinematics.
Before coming to SUTD, I worked as a postdoctoral research associate at University of Cambridge. I received my PhD degree from University of Oxford, working on statistical Chinese processing for my thesis. I received my MSc degree from University of Oxford, working on statistical machine translation from Chinese to English by parsing. I received my undergraduate degree on Computer Science from Tsinghua University, China.
ZPar: statistical multi-language parser, with language-specific support for Chinese and English. ZPar gives state-of-the-art speed and accuracies for Chinese and English on standard Penn Chinese Treebank and Penn Treebank test data. It provides integrated systems that perform word segmentation, part-of-speech tagging, dependency parsing or phrase structure parsing. ZPar has also been used for the syntactic analysis of Romanian, French and other languages. ZPar is fast, processing above 50 sentences per second using the standard Penn Treebank (Wall Street Journal) data.
- Yue Zhang and Stephen Clark. 2011. Syntactic Processing Using the Generalized Perceptron and Beam Search. InComputational Linguistics, 37(1), March.
Please refer to my homepage for more detailed information.