Position: Home > Faculty > Full Professor > Z > Content

Xiaoyan ZHU

Apr 6, 2021 11:30

职称 Professor 部门 Department of Computer Science and Technology
加盟部门 1993 邮箱 zxy-dcs@tsinghua.edu.cn
电话 +86-10-62796831


Education background

Bachelor of Automation, University of Science and Technology Beijing, China, 1981;

Master of Automation, Kobe University, Japan, 1989;

Ph.D. in Information Engineering, Nagoya Institute of Technology, Japan, 1990.

Social service

Beijing Computer Federation: Deputy Director (2004-2018);

Department of Computer Science and Technology, Tsinghua University: Vice Dean (2004-2007);

State Key Laboratory of Intelligent Technology and System, Tsinghua University: Deputy Director (2002-).

Areas of Research Interests/ Research Projects

Machine Learning, Text Information Processing, Conversational AI, Dialogue System

National Basic Research Program of China (The 973 Program): Large-Scale and Real-Text Oriented Chinese Computing: Theories, Methods and Tools (1998-2002);

National 863 High-Tech Program: Research on Bio-Information: Extraction, Evaluation and Integration (2007-2008);

International Project funded by International Development and Research Center (Canada): Breaking the Barriers to Internet Access (2009-2014).

Research Status

Over the years, my research team and I have devoted ourselves to various aspects of artificial intelligence. In recent years, we have mainly focused on Conversational AI. In history, research has also been carried out in the fields of Opinion Mining and Analysis, Text Summarization, Bioliterature Mining, Speech Processing, Optical Character Recognition, etc.

Since 2005, research has been focused on Text mining, Text summarization, Opinion Mining and Analysis, Question Answering/Dialogue System, Conversational AI, and so on. From the perspective of theory research, we did a lot work based on the concept of information distance. To measure informational similarity between individual objects, we proposed conditional information distance model, MIN information distance model and multiple-object information distance model, respectively. These models extend the traditional information distance theory, and provide creative and effective ways to practical application. We have successfully applied these models to many text mining tasks such as pattern optimization in biomedical text mining, information distance between a question and its answer in QA, content similarity measurement in multiple document summarization, and typical/overall document extraction in product review summarization. Our multiple-document summarization system successively ranked 1st in TAC (Text Analysis Conference) 2008 and 2009, a well-recognized international evaluation for Natural Language Processing methodologies. At the same time, as fundamental application research, a series of researches have been carried out around multiple tasks of natural language processing, and nearly 100 papers have been published, including ACL2012 best student paper, COLING2010 best paper, KDD2008 best paper candidate, IJCAI2018 outstanding paper. With the support of these basic research results, we have also achieved many good results in international competitions, including first place in international competition Biocreative II2005, first place in the international text summary evaluation competition TREC2007, and 2008, respectively. We also developed a number of platforms such as the platform for opinion mining, and dialogue system research and development. And we also developed several prototype systems, including an open domain question and answer system and vertical domain dialogue systems.

Before 2004, my group focused on Optical Character Recognition (OCR), Speech Signal Processing and Human-Computer Interaction. The theoretical achievements of our work have been applied to two systems-OCR Engine (a system for handwritten character recognition) and Aurora (a system developed for blind and visually impaired computer users). Thanks to our OCR Engine's high accuracy, it had been used in the Fifth National Census of China in 2000. The Aurora system provides users with a set of helpful tools including screen reader, speech recognition server, Braille translator, and email editor. Aurora has a large population of organizational (schools for the blind) and individual users in China, and was adopted by China's First Computer Certification Test for the Blind.

Honors And Awards

Science and Technology Progress Award by Ministry of Education, Second Class-An Off-line Handwriting Recognition System for Chinese Characters and Numbers (1997);

National Award for Science and Technology Progress, Second Class-OCR Character Input System for the Fifth Census in China (2004);

IDRC Research Chair in Information Technology (2009).

Academic Achievement

[1] Minlie Huang, Qiao Qian, Xiaoyan Zhu. Encoding Syntactic Knowledge in Neural Networks for Sentiment Classification. ACM Trans. Inf. Syst. 35, 3, Article 26 (June 2017), 27 pages

[2] Pei Ke*, Jian Guan*, Minlie Huang, Xiaoyan Zhu. Generating Informative Responses with Controlled Sentence Function. ACL 2018, Melbourne, Australia.

[3] Hao Zhou*, Tom Yang*, Minlie Huang, Haizhou Zhao, Jingfang Xu, Xiaoyan Zhu. Commonsense Knowledge Aware Conversation Generation with Graph Attention. IJCAI-ECAI 2018, Stockholm, Sweden.

[4] Ryuichi Takanobu*, Minlie Huang, Zhongzhou Zhao, Fenglin Li, Haiqing Chen, Xiaoyan Zhu, Liqiang Nie. A Weakly Supervised Method for Topic Segmentation and Labeling in Goal-oriented Dialogues via Reinforcement Learning. IJCAI-ECAI 2018, Stockholm, Sweden

[5] Jun Feng*, Minlie Huang, Li Zhao, Yang Yang, Xiaoyan Zhu. Reinforcement Learning for Relation Classification from Noisy Data. AAAI 2018, New Orleans, Louisiana, USA.

[6] Hao Zhou*, Minlie Huang, Xiaoyan Zhu, Bing Liu. Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory. AAAI 2018, New Orleans, Louisiana, USA

[7] Jun Feng*, Heng Li, Minlie Huang, Shichen Liu, Wenwu Ou, Zhirong Wang and Xiaoyan Zhu. Learning to Collaborate: Multi-Scenario Ranking via Multi-Agent Reinforcement Learning. WWW 2018 (Industry Track). Lyon, France.

[8] Qiao Qian, Minlie Huang, Xiaoyan Zhu. Linguistically Regularized LSTM for Sentiment Analysis. ACL 2017.

[9] Han Xiao, Minlie Huang and Xiaoyan Zhu. SSP: Semantic Space Projection for Knowledge Graph Embedding with Text Descriptions. AAAI 2017. February 4–9, San Francisco, US.

[10] Han Xiao, Minlie Huang, Xiaoyan Zhu. TransG : A Generative Model for Knowledge Graph Embedding.. ACL 2016, Berlin, Germany. [PDF]

[11] Han Xiao, Minlie Huang, Xiaoyan Zhu. From One Point to A Manifold: Knowledge Graph Embedding For Precise Link Prediction. IJCAI 2016, New York, USA.[PDF]

Previous:Wenwu ZHU

Next:Xiaoping ZHANG