Dr Zong Chengqing

CSIDM-200804

Address: National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences No. 95, Zhongguancun Donglu, Haidian District, Beijing 100190, China

E-mail:  cqzong@nlpr.ia.ac.cn
Tel. No.:  +86-10-6255 4263 
Fax:     +86-10-6255 1993
Homepage: http://www.nlpr.ia.ac.cn/cip/english/Zong_Eng.htm

PROFESSIONAL EXPERIENCE:

  • April 2000 – Now: Research Fellow, National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA). Now he is a professor and deputy director of NLPR.
  • October 2004 – January 2005, Visiting Scholar, GETA, CLIPS-IMAG, France
  • April 2001 – September 2001: Guest Researcher, SLT-ATR, Japan
  • May 1999 – August 1999: Guest Researcher, SLT-ATR, Japan
  • May 1998 – April 2000: Post-Doctoral Research Fellow, NLPR, CASIA.
  • July 1990 – March 1995: Teacher, Department of Computer Engineering, Shandong University of Technology, China

EDUCATION:

March 1995 – March 1998: Ph.D. Candidate, Institute of Computing Technology, Chinese Academy of Sciences (CAS). September 1987 – July 1990: Master Student, Department of Computer Engineering, Shandong University of Technology, China. September 1983 – July 1987: Student, Department of Computer Engineering, Shandong University of Technology, China.

HONORS:

K. C. Wong Post-doctoral Research Award Fund, CAS, December 1998. Shenzhen Huawei Prize for Excellent Ph.D. Candidate, CAS, March 1998.

PUBLICATIONS:

BOOK:

Chengqing Zong, Statistical Natural Language Processing (in Chinese), (ISBN: 978-7-302-16598-9), Tsinghua University Press, May 2008.

PAPERS:

INTERNATIONAL PAPERS

[1] Chengqing Zong, Qingshi Gao. Chinese R&D in Natural Language Technology. IEEE Intelligent Systems, Vol.23, No. 6, 2008. Pages 42-48

[2] Yufeng Chen, and Chengqing Zong. A Structure-based Model for Chinese Organization Name Translation. ACM Transactions on Asian Language Information Processing, 7(1): 1-30, February 2008

[3] Shoushan Li, and Chengqing Zong. Multi-domain Sentiment Classification (short paper). In Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technology (ACL-08: HLT), Short Papers (Companion Volume), pages 257-260. Columbus, Ohio, USA. June 15-20, 2008

[4] Jiajun Zhang, Chengqing Zong, Shoushan Li. Sentence Type Based Reordering Model for Statistical Machine Translation. In Proceedings of Conference on Computational Linguistics (COLING), August 18-22, 2008. Manchester, UK.

[5] Hua Wu, Haifeng Wang, and Chengqing Zong. Domain Adaptation for Statistical Machine Translation with Domain Dictionary and Monolingual Corpora. In Proceedings of Conference on Computational Linguistics (COLING), August 18-22, 2008. Manchester, UK.

[6] Xiaofeng Wu, and Chengqing Zong. A New Approach to Automatic Document Summarization. In Proceedings of the International Joint Conference on Natural Language Processing (IJCNLP), Hyderabad, India, January 8-10, 2008. Pages 126-132

[7] Yanqing He, and Chengqing Zong. A Generalized Reordering Model for Phrase-Based Statistical Machine Translation. In Proceedings of the 8th Conference of the Association for Machine Translation in the Americas, October 21-25, 2008. Waikiki, Hawai'i, USA.

[8] Licheng Fang, and Chengqing Zong, Rile Hu, and Xia Wang. An Efficient Approach to Redundancy Reduction in Hierarchical Phrase-Based Translation. In Proceedings of the IEEE Conference on Natural Language Processing and Knowledge Engineering (NLP-KE), October 19-22, 2008. Beijing, China.

[9] Shoushan Li, and Chengqing Zong. Multi-domain Adaptation for Sentiment Classification: Using Multiple Classifier Combining Methods. In Proceedings of the IEEE Conference on Natural Language Processing and Knowledge Engineering (NLP-KE), October 19-22, 2008. Beijing, China.

[10] Yanqing He, Jiajun Zhang, Maoxi Li, Licheng Fang, Yufeng Chen, Yu Zhou, and Chengqing Zong. The CASIA Statistical Machine Translation System for IWSLT 2008. In Proceedings of the International Workshop of Spoken Language Translation (IWSLT), October 20-21, 2008. Waikiki, Hawai'i, USA.

[11] Shoushan Li, and Chengqing Zong. Classifier Combining Rules Under Independence Assumptions. In Proceedings of the 7th International Workshop on Multiple Classifier Systems (MCS), Prague, Czech Republic, May 23-25, 2007. Pages 322-332.

[12] Shoushan Li, Chengqing Zong, and Xia Wang. Sentiment Classification through Combining Classifiers with Multiple Feature Sets. In Proceedings of IEEE International Conference on Natural Language Processing and Knowledge Engineering (NLP-KE), August 30-Sept. 1, 2007, Beijing. Pages 135-140.

[13] Yu Zhou, Yanqing He, and Chengqing Zong, The CASIA Phrase-Based Statistical Machine Translation System for IWSLT 2007. In Proceedings of the International Workshop on Spoken Language Translation (IWSLT), October 15-16, 2007, Trento, Italy.

[14] Rile Hu, Chengqing Zong, and Bo Xu. An Approach to Automatic Acquisition of Translation Templates Based on Phrase Structure Extraction and Alignment. IEEE Transaction on Audio, Speech, and Language Processing. Vol. 14, No.5, September 2006.

[15] Sebastian Stüker, Chengqing Zong, Jürgen Reichert, Wenjie Cao, Muntsin Kolss, Guodong Xie, Kay Peterson, Peng Ding, Victoria Arranz, Jian Yu, and Alex Waibel. Speech-to-Speech Translation Services for the Olympic Games 2008. In Proceedings of the 3rd Joint Workshop on Machine Learning and Multimodal Interaction (MLMI), 1-3 May 2006, Washington DC, USA.

[16] Fang Xu, Chengqing Zong, and Jun Zhao. A Hybrid Approach to Chinese Base Noun Phrase Chunking. In Proceedings of the 5th SIGHAN Workshop on Chinese Language Processing, pages 87-93, Sydney, July 22-23, 2006.

[17] Chengqing Zong, and Mark Seligman. Toward Practical Spoken Language Translation. Machine Translation, 19(2): 113-137. June 2005.

[18] Cao Wenjie, Chengqing Zong, and Bo Xu. Investigation of Emotive Expressions of Spoken Sentences. In Affective Computing and Intelligent Interaction (Proceedings of the First International Conference, ACII, October 22-24, 2005, Beijing, China) (Jianhua Tao, Tieniu Tan and Rosalind W. Picard (Eds.). Springer. Pages 972-980.

[19] Yu Zhou, Chengqing Zong, and Bo Xu. Various Aligned Models In Chinese-to-English Statistical Machine Translation. In Proceedings of the IEEE International Conference on Natural Language Processing and Knowledge Engineering (NLP-KE). October 30th - November 1st, 2005. Wuhan, China. Pages 443-448.

[20] Shoushan Li, and Chengqing Zong. A New Approach to Feature Selection for Text Categorization. In Proceedings of the IEEE International Conference on Natural Language Processing and Knowledge Engineering (NLP-KE). October 30th - November 1st, 2005. Wuhan, China. Pages 626-630.

[21] Xing Li, and Chengqing Zong. A Hierarchical Parsing Approach with Punctuation Processing for Long Complex Chinese Sentences. In In Companion Volume to the Proceedings of Conference including Posters/Demos and Tutorial Abstracts, IJCNLP2005, Jeju Island, Korea, October 11-13, 2005. Pages 9-14.

[22] Wenjie CAO, Chengqing Zong, and Bo XU. Approach to Interchange-Format Based Chinese Generation. In Proceedings of the International Conference on Spoken Language Processing (ICSLP). October 4-8, 2004. Jeju, Korea. Pages 194-197.

[23] Rile Hu, Chengqing Zong, and Bo Xu. Approach to Automatic Translation Template Acquisition Based on Unannotated Bilingual Grammar Induction. In Proceedings of the International Workshop on Machine Translation and Multilingual Information Retrieval (MTMIR), Sanya, Hainan, China, 2004.

[24] Yu Zhou, Chengqing Zong, and Bo Xu. Bilingual Chunk Alignment in Statistical Machine Translation. In Proceedings of IEEE International Conference on Systems, Man & Cybernetics (SMC2004), Hague, Netherlands, 2004.

[25] Guodong Xie, Chengqing Zong, and Bo Xu. Approach to Robust Spoken Chinese Language Parsing (in Chinese). Journal of Chinese Language and Computing, 14 (1): 5-19, 2004. Singapore.

[26] Wenjie CAO, Chengqing Zong, and Bo XU. Approach to Chinese and English Language Generation Based on Interchange Format (in Chinese). Journal of Chinese Language and Computing, 14(1): 21-34, 2004. Singapore.

[27] Chengqing Zong, and Fuji Ren. Chinese Utterance Segmentation in Spoken Language Translation. In Proceedings of the 4th International Conference on Computational Linguistics and Intelligent Text Processing (CICLing-03). Feb. 16-22, 2003. Mexico. Pages 516-525.

[28] Guodong Xie, Chengqing Zong, and Bo Xu. A Maximum Entropy Approach for Spoken Chinese Understanding”. In Proceedings of the 4th International Conference on Computational Linguistics and Intelligent Text Processing (CICLing-03). Feb. 16-22, 2003. Mexico. Pages 91-100.

[29] Keli Chen, and Chengqing Zong. A New Weighting Algorithm for Linear Classifier. In Proceedings of the international conference on Natural Language Processing and Knowledge Engineering (NLP-KE). Oct. 26-29, 2003. Beijing. Pages 650-655.

[30] Rile Hu, Chengqing Zong, and Bo Xu. Semiautomatic Acquisition of Translation Templates from Monolingual Unannotated Corpora. In Proceedings of the International Conference on Natural Language Processing and Knowledge Engineering (NLP-KE). Oct. 26-29, 2003. Beijing. Pages 163-167.

[31] Ding Liu, and Chengqing Zong. Utterance Segmentation Using Combined Approach Based on Bi-directional N-gram and Maximum Entropy. In Proceedings of ACL-2003 Workshop: The Second SIGHAN Workshop on Chinese Language Processing, July 11-12, 2003. Sapporo, Japan. Pages 16-23.

[32] Ding Liu, Yu Zhou, Chengqing Zong, and Fuji Ren. Automatic Evaluation of Sentence Fluency. In Proceedings of 2003 IEEE International Conference on Systems, Man and Cybernetics (SMC). October 5-8, 2003. Washington, D.C., USA. Pages 1687-1692.

[33] Ying Liu, and Chengqing Zong. Rule Base Combined Linguistics Knowledge with Corpus. In Proceedings of 2003 International Conference on Systems, Man and Cybernetics (SMC). October 5-8, 2003. Washington, D.C., USA. Pages 5022-5027.

[34] Chengqing Zong, Yujie Zhang, Kazuhide Yamamoto, Masashi Sakamoto and Satoshi Shirai. Chinese Utterance Paraphrasing for Spoken Language Translation (in Chinese). Journal of Chinese Language and Computing, 2002,12 (1): 63-77.

[35] Chengqing Zong, Bo Xu, and Taiyi Huang. 2002. Interactive Chinese-to-English Speech Translation Based on Dialogue Management. In Proceedings of ACL’2002 Workshop- Speech-to-speech Translation: Algorithms and Systems. July 11, 2002. Philadelphia, USA. Pages 61-68.

[36] Yan Zhang, Bo Xu, and Chengqing Zong. Chinese Syntactic Parsing Based on Extended GLR Parsing Algorithm with PCFG*. In Proceedings of the 19th International Conference on Computational Linguistics (COLING’2002). August 24 - Sept.1, 2002, Taiwan. Pages 1318-1332.

[37] Guodong Xie, Chengqing Zong, and Bo Xu. Chinese Spoken Language Analyzing Based on Combination of Statistical and Rule Methods. In Proceedings of the International Conference of Spoken Language Processing (ICSLP’2002). Sept. 16-20, 2002. Colorado, USA. Pages 613-616.

[38] Wen-Jie Cao, Chengqing Zong, Juha Iso-Sipild, and Bo Xu. Chinese Person Name Identification Based on Rules and Statistics. In Proceedings of the International Symposium on Chinese Spoken Language Processing (ISCSLP), August 22-24, 2002, Taiwan. Pages 331-334.

[39] Rile HU, Chengqing Zong, Juha Iso-Siila, and Bo Xu. Investigation and Analysis on Designing Chinese Balance Corpus. In Proceedings of the International Symposium on Chinese Spoken Language Processing (ISCSLP), August 22-24, 2002, Taiwan. Pages 335-338.

DOMESTIC PAPERS

[1] Fang Xu, Chengqing Zong，and Xia Wang. Chinese Base NP Chunking by Error-driven Combination Classifiers (in Chinese). Journal of Chinese Information Processing, No. 1, Vol. 21, 2007. Pages 115-119.

[2] He Yanqing, Zhou Yu, Zong Chengqing, and Wang Xia. A Flexible-Scale-Based Method of Phrase Translation Extraction (In Chinese). In Journal of Chinese Information Processing, 2007. 21(5): 91-95.

[3] Yuncun Zuo, and Chengqing Zong. Approach to Chinese Spoken Language Parsing Based on Semantic Classification Tree (in Chinese). Journal of Chinese Information Processing, No. 2, Vol. 20, 2006. Pages 8-15.

[4] Xing Li, and Chengqing Zong. A Hierarchical Parsing Approach with Punctuation Processing for Long Chinese Sentences (in Chinese). Journal of Chinese Information Processing, No. 4, Vol. 20, 2006. Pages 8-15.

[5] Yu Zhou, Chengqing Zong, and Bo Xu. Multi-Layer Filtering Based Statistical Machine Translation (in Chinese). Journal of Chinese Information Processing, No. 3, Vol. 19, 2005. Pages 54-60.

[6] Rile Hu, Chengqing Zong, and Bo Xu. Approach to Automatic Translation Template Acquisition Based on Statistical Learning (in Chinese). Journal of Chinese Information Processing, No. 6, Vol. 19, 2005. Pages 1-6.

[7] Guodong Xie, Chengqing, Zong, and Bo Xu. Chinese Spoken Language Analyzing Oriented to Middle Semantic Representation (in Chinese). Journal of Chinese Information Processing, No. 1, Vol. 17, 2003. Pages 1-6.

[8] Yan Zhang, Chengqing, Zong, and Bo Xu. Structure Analysis and Extraction for Definitions of Chinese Terms (in Chinese). Journal of Chinese Information Processing, No. 6, Vol. 17, 2003. Pages 9-16.

PROFESSIONAL ACTIVITIES

  • Program Committee Member of the 46th Annual Meeting of the Association for Computational Linguistics (ACL): Human Language Technology, June 15-20, 2008. Ohio, USA.
  • Program Committee Member of the 22nd Conference on Computational Linguistics (COLING), August 18-22, 2008. Manchester, UK.
  • Program Committee Co-Chair of IEEE International Conference on Natural Language Processing and Knowledge Engineering (NLP-KE). October 19th – 22nd , 2008, Beijing, China.
  • Program Committee Co-Chair of the IEEE International Conference on Natural Language Processing and Knowledge Engineering (NLP-KE). August 30th - September 1st, 2007, Beijing, China.
  • Program Committee Member of the International Conference on Chinese Computing (ICCC), October 13-15, 2007, Wuhan, China.
  • Evaluation Committee Member of the International Workshop on Spoken Language Translation (IWSLT), October 15-16, 2007. Trento, Italy.
  • Program Committee Member of the International Workshop on Spoken Language Translation (IWSLT), November 27-28, 2006. Kyoto, Japan.
  • Program Committee Member of TC-STAR Workshop on Speech-to-speech Translation, June 19-21, 2006. Barcelona, Spain.
  • Program Committee Co-Chair of the IEEE International Conference on Natural Language Processing and Knowledge Engineering (NLP-KE). October 30th-November 1st, 2005. Wuhan, China.
  • Program Committee Member and Organization Committee Member of the International Workshop on Spoken Language Translation (IWSLT), October 24-25, 2005. Pittsburgh, USA.
  • Program Committee Member of the 3rd International Workshop on Paraphrasing (IWP), October 14, 2005. Jeju Island, Korea.
  • Program Committee Member of the International Workshop on Representing Discourse and Dialog Related Phenomena for Speech-to-Speech (Interlingual) Machine Translation Systems, in conjunction with the MT Summit X, September 16, 2005. Phuket, Thailand.
  • Program Committee Member of the International Conference on Chinese Computing (ICCC), March 21-23, 2005. Singapore.
  • Speech Area Co-Chair of the First International Joint Conference on Natural Language Processing (IJCNLP). March 22nd – 24th, 2004. Sanya, China.
  • Program Committee Co-Chair of 2003 International Conference on Natural Language Processing and Knowledge Engineering (NLP-KE). Oct. 26th – 29th, 2003, Beijing, China.
  • Program Committee Member of International Workshop of Paraphrasing (IWP). July 11, 2003. Sapporo, Japan.
  • Member of Technical Committee of Human-Computer Interaction (TC-13), International Federation for Information Processing (IFIP), August 2005 - Now
  • Member of Editorial Board, Journal of Chinese Language and Computing (Singapore), Dec. 2002 – now
  • Member of Editorial Board, Information (Japan), January 2002 – now
  • Member of Editorial Board, Intelligent Technology (in Chinese), Feb. 2006 - now
  • Guest Professor at Tsinghua University, January 2004 – now
  • Adjunct Professor at Graduate School of the Chinese Academy of Sciences, September 2005 – now
  • Adjunct Professor at Beijing University of Post and Telecommunications, January 2006 – now
  • Adjunct Professor at Shandong University, October 2005 – now
  • Standing Member of the Chinese Association of Artificial Intelligence, November 2005 – now
  • Standing Member of the Society of Chinese Information Processing of China, November 2006 – now

TEACHING COURSES

  • Natural Language Understanding, for graduate students of the Graduate School, Chinese Academy of Sciences, 2004, 2005, 2006, 2007, 2008, 5 classes in five terms, about 280 students in total;
  • Principles and Techniques of Computer Compilation, for undergraduate students of Department of Computer Engineering, Shandong University of Technology, 1992, 1993, 1994, about 180 students in 3 classes, 3 terms in total;
  • Discrete Mathematics, for undergraduate students of Department of Computer Engineering, Shandong University of Technology, 1992, about 40 students in one class, one term;
  • C Language Programming, for undergraduate students of Department of Computer Engineering, Shandong University of Technology, 1991, about 40 students in one class, one term;
  • Principles of Database System, for undergraduate students of Department of Computer Engineering, Shandong University of Technology, 1990, about 80 students in two class, one term.
  • From 2001 to 2007, he has supervised 8 Master degree students and 13 Ph.D. candidates in NLPR of CASIA.

    PROJECTS

Key Technology Research and Development for Multilingual Information Service

TIME: Dec. 1, 2006 – Dec. 31, 2009
SOURCES OF FUNDING: National Key Technology R&D Program of China

ABSTRACT: Oriented to the scientific and technical information accessing, the key technologies and application tools will be developed in this project, which are used for English-Chinese machine assisted translation and Chinese-English cross-lingual information retrieval. An integrated experimental system of scientific and technical information service also will be developed. Results of the project will provide a solid foundation for multilingual information service in the area of science and technology.

Research on Key Techniques of Spoken Language Translation Oriented to Networking

TIME:  Dec. 1, 2006 – Dec. 31, 2008
SOURCES OF FUNDING:  High-Tech. Program of China (863 Program)

Oriented to the cross-lingual communications in the environment of networking, this project focuses on the research of key techniques and implementation of practical spoken language translation (SLT) system. The following problems are addressed: (1) rhythm modeling of spoken Chinese language and new approach establishing for robust spoken language recognition; (2) new approach to discourse analysis and translation; (3) integration of possible practical SLT system using current immature techniques; (4) experiment of Chinese-English SLT in the environment of networking.

Approach To Interactive Spoken Language Translation Based on Dialogue Understanding

TIME: Jan. 1, 2005 – Dec. 31, 2008
SOURCES OF FUNDING: Natural Science Foundation of China

The purpose of this project is to study some key technologies in the spoken language translation (SLT), to improve the translation quality and enhance the robustness of the SLT system. The main tasks of this project include: (1) Collect the large scale spoken Chinese-English parallel corpora; (2) Study the robust parsing approach to the speech recognition results with noisy words; (3) Study the robust parsing approach to the long ill-formed Chinese utterances; (4) Study the theory of human-computer interaction and develop the experimental Chinese-to-English SLT system.

Robust Approach to Information Extraction Based on Dialogue Content

TIME: Jan.1, 2004 – Dec. 31, 2006
SOURCES OF FUNDING: Natural Science Foundation of China

Oriented to the national information security, this project is aiming to explore the method of automatically monitoring the content of the dialog between two speakers and creating the summarization of the dialogue. Regarding to the object, we are engaged in the research on the theory of dialog analysis and understanding, and also the implementation technology of dialog monitoring and summarization as well. A robust experiment platform for automatically extracting spoken Chinese dialog will be developed. The research in this project is not only of the great scientific and practical value in advancing the development of natural language processing and Chinese information processing, but also very meaningful to protect the national security. We believe that the technology addressed in this project will be widely used in many domains of information service and it is very probable to make great economical benefit.

Research on Robust Schematic Approach to Spoken Chinese Parsing Based on Children Psychologic Analysis

TIME: Jan. 1, 2002 – Dec. 31, 2004
SOURCES OF FUNDING: Natural Science Foundation of China

This project aims at the research on the approach to the robust natural spoken language automatic parsing and exploring a new theory and method of automatic understanding the schematic spoken Chinese language based on the children psychology analysis. The method tries to start with the basic psychology of children’ learning language to grope for a new way of spoken language semantic schematic expression. Its main idea is combining the semantic analytical mechanism with the geometry graph to establish the robust automatic obtaining strategy of spoken language semantic analysis. This research is very meaningful and practical to promote the research of information processing of the spoken Chinese language.