Sun, Xu
Associate Professor with Tenure
Research Interests: Natural language processing, machine learning
Office Phone: 86-10-6276 5835-103
Email: xusun@pku.edu.cn
Sun, Xu got Ph.D from The University of Tokyo (2010), M.S. from Peking University (2007), and B.E. from Huazhong Univ. of Sci. & Tech. (2004). From 2010 to 2012, he worked at The University of Tokyo, Cornell University, and The Hong Kong Polytechnic University as Research Fellow/Associate. His research focuses on natural language processing and machine learning, especially on structured natural language processing and structured learning.
Dr. Sun has published more than 30 research papers, and most of them are published in top-tier conference and journals, such as ACL, NIPS, TKDE, and CL. He has served in the Technical Program Committee of various international conferences including ACL, IJCAI, AAAI, COLING, EMNLP, and NAACL. He has been Area Chair of EMNLP and IJCNLP. He has been journal reviewer of IEEE TPAMI, CL, and so on. He was awarded Qiu Shi Outstanding Young Scholar Award (2015).
Dr. Sun has hosted and participated in several state research projects, including NSFC, 863 project, etc. His major achievements in research are summarized as follows:
1) Theories and methods of structured learning: This is the fundamental of structured natural language processing. He proposed the theory of structure-based risk and some scalable and efficient learning methods, which support the learning of NLP tasks. Natural language often exhibits sophisticated structures. He proposed several methods for modeling different kinds of structures in structured learning, including deep structures, complex structures and hidden structures. These methods facilitate the research and application in NLP tasks.
2) Structured NLP applications: The theories and methods proposed are adapted to solve the real-world NLP tasks of different levels, including word-level, phrase-level, and document level. He designed new methods for various NLP tasks such as chunking, word segmentation, named entity recognition, abbreviation generation, and automatic summarization of social media documents, which achieve state of the art or even better results. He proposed new techniques to solve the query-related analysis of sentences and documents. These techniques can improve the end user tasks, such as search engine, summarization and machine translation.
