教师名录

姚 天昉 副教授

主页:

办公室电话:+86-21-3420-5213

办公地点:SEIEE-3-523

电子邮件:yao-tf@cs.sjtu.edu.cn

实验室: 中德语言技术联合实验室

  • 研究兴趣
  • 教育背景
  • 工作经验
  • 教授课程
  • 论文发表
  • 项目资助
  • 获奖信息
  • 学术服务
Language Technology and Application including:
Opinion Mining, Information Extraction, 
Machine Learning, Information Retrieval, 
Ontology Learning, 
Natural Language Generation
Ph.D., Scientific-Technical Faculty I: Mathematics and Computer Science, Saarland University, Saarbrücken, Germany. 2005.
Thesis: A Study of Chinese Named Entity and Relation Identification in a Specific Domain
Supervisors:  
Prof. Dr. Hans Uszkoreit
Prof. Dr. Wolfgang Wahlster
1999 – 2004: Ph.D. Candidate in the Department of Computer Science / Computational Linguistics, the University of Saarland, Saarbrücken, Germany.


B.Eng., Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China. 1982. 
Thesis: The Analysis of PASCAL-S Compiler and Its Transplantation
Supervisors:  
Prof. Gao Hanqing
Prof. Liang Jinqin
1978 - 1982: Undergraduate Studies at the Department of Computer Science and Engineering of Shanghai Jiao Tong University, Shanghai, China.
2009 - present: Associate Professor and Assistant Dean in the Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China.
2004 - 2009: Associate Professor in the Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China.
2001 - 2004: Research Staff in the Department of Computational Linguistics, the University of Saarland, Saarbrücken, Germany. 
1999 - 2001: Visiting Scholar in German Research Center for Artificial Intelligence (DFKI), Saarbrücken, Germany.
1995 - 1999: Vice Chairman, Associate Professor and Project Leader in the Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China.
1993 - 1995: Associate Professor in the Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China.
1990 - 1993: Lecturer in the Department of Computer Science and Engineering,  Shanghai Jiao Tong University, Shanghai, China.
1988 - 1990: Guest Researcher in China Commission, the University of Constance, Constance, Germany. 
1987 - 1988: Lecturer in the Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China.
1982 - 1987: Assistant in the Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China
SS 2012
Course "C++ Programming", SJTU, Shanghai, China
Course "Web Mining"(Postgraduate), SJTU, Shanghai, China
WS 2011/12
Course "Introduction to Computation", SJTU, Shanghai, China
SS 2011
Course "C++ Programming", SJTU, Shanghai, China
Course "Web Mining"(Postgraduate), SJTU, Shanghai, China
Course "Natural Language Understanding"(Postgraduate), SJTU, Shanghai, China
WS 2010/11
Course "Programming Thinking and Method" , SJTU, Shanghai, China
SS 2010
Course "C++ Programming", SJTU, Shanghai, China
Course "Web Mining"(Postgraduate), SJTU, Shanghai, China
WS 2009/10
Course "Object-Oriented Analysis and Design", SJTU, Shanghai, China
Course "Internet-based Information Extraction Technology", SJTU, Shanghai, China
SS 2009
Course "Web Mining"(Postgraduate), SJTU, Shanghai, China
Course "Data Warehouse and Data Mining"(Postgraduate), SJTU, Shanghai, China
Course "Database", SJTU, Shanghai, China
WS 2008/09
Course "Object-Oriented Analysis and Design", SJTU, Shanghai, China
Course "Internet-based Information Extraction Technology", SJTU, Shanghai, China
Course "Data Warehouse and Data Mining"(Postgraduate), SJTU, Shanghai, China
SS 2008
Course "Web Mining"(Postgraduate), SJTU, Shanghai, China
WS 2007/08
Course "Internet-based Information Extraction Technology" , SJTU, Shanghai, China
Course "Principles of Database", SJTU, Shanghai, China 
SS 2007
Course "Data Warehouse and Data Mining"(Postgraduate), SJTU, Shanghai, China
Course "Web Mining"(Postgraduate), SJTU, Shanghai, China
WS 2006/07
Course "Natural Language Understanding", SJTU, Shanghai, China
Course "Internet-based Information Extraction Technology", SJTU, Shanghai, China
SS 2006
Course "Web Mining"(Postgraduate), SJTU, Shanghai, China
WS 2005/06
Course "Natural Language Understanding", SJTU, Shanghai, China
Course "Internet-based Information Extraction Technology", SJTU, Shanghai, China
SS 2005
Course "Design of Large-Scale Application Software", SJTU, Shanghai, China
WS 2004/05
Course "Natural Language Understanding", SJTU, Shanghai, China
Course "Internet-based Information Extraction Technology", SJTU, Shanghai, China
Opinion Mining
■ 卡哈尔江?阿比的热西提,吐尔根?依布拉音,姚天昉,艾山?吾买尔,艾山?毛力尼亚孜. 一种改进的维吾尔语句子相似度计算方法.中文信息学报. 第25卷第4期. 2011年7月. 第50页-53页.
■ 刘军,姚天昉,仇伟. 意见时空元素的研究. 中文信息学报. 第25卷第3期. 2011年5月. 第72页-78页.
■ 李婷玉,葛正荣,姚天昉. 汉语情感问题类型分类研究. 中文信息学报. 第25卷第2期. 2011年3月. 第94页-98页.
■ 刘全升,姚天昉. 基于关联度模型的文本倾向性检索研究. 中文信息学报. 第25卷第1期. 2011年1月. 第15页-19页.
■ Hongyan Song and Tianfang Yao. Active Learning Based Opinion Element Identification. Proceeding of the 2010 IRAST International Congress on Computer Application and Computational Science (CACS 2010). Dec. 4-6, 2010, Singapore. pp. 716-719.
■ 栾家阳,张文波,姚天昉. 基于汽车领域的情感问答系统设计与实现. 第五届全国青年计算语言学研讨会论文集. 武汉. 2010年10月. 第459-465页.
■ 葛正荣,李婷玉,姚天昉. 汉语情感问题类型分类研究. 第五届全国青年计算语言学研讨会论文集. 武汉. 2010年10月. 第324-330页.
■ Mosha Chen and Tianfang Yao. Combining Dependency Parsing with Shallow Semantic Analysis for Chinese Opinion-Element Relation Identification. Proceeding of the 2010 4th International Universal Communication Symposium. Oct. 18 - 19, 2010, Beijing, China. pp. 298-304.
■ 刘军,姚天昉. 利用Wikipedia计算语义相似度. 计算机工程. 第36卷第19期. 2010年10月. 第42-43页.
■ Hongyan Song and Tianfang Yao. Active Learning Based Corpus Annotation. Proceeding of the CIPS-SIGHAN Joint Conference on Chinese Language Processing. Aug. 28-29, 2010, Beijing, China. pp. 159-166.
■ 刘全升,姚天昉. 基于关联度模型的文本倾向性检索研究. 第六届全国信息检索学术会议(CCIR 2010)论文集. 镜泊湖. 2010年8月. 第699-706页.
■ 仇伟,黄高辉,姚天昉. 基于HowNet的汉语情感问句二层分类. 第六届全国信息检索学术会议(CCIR 2010)论文集. 镜泊湖. 2010年8月. 第618-627页.
■ 黄高辉,姚天昉. 基于CRF算法的汉语比较句识别和关系抽取. 计算机应用研究. 2010年第6或7期. 第27卷第6期. 2010年6月. 第2061-2064页.
■ Hongyan Song and Tianfang Yao. Improving Chinese Topic Extraction Using Word Sense Disambiguation Information. In Proc of the Fourth International Conference on Innovative Computing, Information and Control. December 7 - 9, 2009, Kaohsiung, Taiwan.
■ 陈漠沙,王睿,张潇君,仇伟,章毅,李婷玉,张文波,姚天昉. Analysis of the Evaluation Results for our Tasks in COAE2009. 第二届中文倾向性分析评测研讨会(COAE2009)论文集. 上海,2009年11月. 第134-143页.
■ 许洪波,姚天昉,黄萱菁,唐慧丰,关峰,张瑾. 第二届中文倾向性分析评测技术报告. 第二届中文倾向性分析评测研讨会(COAE2009)论文集. 上海,2009年11月. 第1-23页.
■ 陈奇哲 刘全升 姚天昉. 汉语意见型语句主题与情感成分及关系抽取的研究. 第五届全国信息检索学术会议(CCIR’2009)论文集. 上海, 2009年11月.第504-512页.
■ 王睿,章毅,仇伟,陈漠沙,李婷玉,张文波,姚天昉. Combining Data-Driven Constituent and Dependency Parsers for CIPS-ParsEval-2009. 第一届汉语句法分析评测学术研讨会(CIPS-ParsEval-2009)论文集. 北京,2009年11月. 第138-144页.
■ 姚天昉,张霄凯. 一种网络非规范汉语词汇的识别方法. 全国第十届计算语言学学术会议(CNCCL-2009) 论文集. 烟台, 2009年7月. 第540 - 545页.
■ 姚天昉,张鑫. 一种基于正例的汉语意见型主观性文本分类方法. 第十二届中国少数民族语言信息处理学术研讨会论文集. 拉萨, 2009年7月.
■ Tianfang Yao and Linlin Li. A Kernel-based Sentiment Classification Approach for Chinese Sentences. In Proc of the 2009 World Congress on Computer Science and Information Engineering (CSIE 2009). Los Angeles, CA, USA. April 2, 2009. pp 513-518.
■ 宋鸿彦,刘军,姚天昉,刘全升,黄高辉. 汉语意见型主观性文本标注语料库的构建. 中文信息学报. 第23卷第二期. 2009年 3月. 123-128.
■ 刘军,刘全升,陈漠沙,宋鸿彦,黄高辉,张潇君,姚天昉. 第一届中文倾向性分析评测结果浅析. 第一届中文倾向性分析评测研讨会论文集. 北京, 2008年11月. 125-141.
■ 刘全升,姚天昉,黄高辉,刘军,宋鸿彦. 汉语意见型主观性文本类型体系的研究. 中文信息学报. 第22卷第六期. 2008年 11月. 63-68.
■ 宋鸿彦,刘军,姚天昉,刘全升,黄高辉. 汉语意见型主观性文本标注语料库构建. 全国第四届信息检索与内容安全会议论文集(上卷). 北京, 2008年11月. 75-81.
■ Hang Yin and Tianfang Yao. Explicit Topic Identification and Analysis for Chinese Opinioned Sentences. In Proc of the 8th International Workshop for Autonomous System – Self-Organization, Management, and Control. Shanghai, China. Oct. 6, 2008. pp 177-183.
■ Xiaokai Zhang and Tianfang Yao. A Study of Network Informal Language using Minimal Supervision Approach. In Proc of the 8th International Workshop for Autonomous System – Self-Organization, Management, and Control. Shanghai, China. Oct. 6, 2008. Springer. pp 169-175.
■ 黄高辉,姚天昉,刘全升. 汉语意见型主观性语句类型分析. 第四届全国学生计算语言学会议论文集. 山西,2008年7月. 208-214.
■ 刘全升,姚天昉,黄高辉,刘军,宋鸿彦. 汉语意见型主观性文本类型体系的研究. 第四届全国学生计算语言学会议论文集. 山西,2008年7月. 215-221.
■ 方习文,姚天昉. 汉语极性词词典的设计和实现. 第一届全国知网研讨会(NHW2008)论文集. 北京,2008年5月. 38-46.
■ 姚天昉,程希文,徐飞玉,汉思?乌思克尔特,王睿. 文本意见挖掘综述. 中文信息学报. 第22卷第三期. 2008年 5月. 71-80.
■ Tianfang Yao, Decheng Lou, Xiwen Fang. Polarity Distinction for Chinese Sentiment Words. In (Eds.): Recent Advance of Chinese Computing Technologies. Chinese and Oriental Language Information Processing Society, Singapore. March, 2008. pp 118-121.
■ 姚天昉,彭思崴. 汉语主客观文本分类特征的研究. 计算机科学,第34卷第12期专刊. 2007年 12月. 176-178.
■ 姚天昉,彭思崴. 汉语主客观文本分类方法的研究. 第三届全国信息检索与内容安全学术会议论文集,苏州,2007年11月. 117-123.
■ 姚天昉,娄德成. 汉语情感词语义倾向判别的研究. 2007中文信息处理国际会议(ICCC2007)论文集,武汉,2007年10月. 221-225.
■ 姚天昉,娄德成. 汉语语句主题语义倾向分析方法的研究. 中文信息学报, 第21卷第五期. 2007年 9月. 73-79.
■ Linlin Li, Tianfang Yao. Kernel-based Sentiment Classification for Chinese Sentence. In Proc. of the 6th International Conference on Advanced Language Processing and Web Information Technology, Luoyang , China . Aug. 22-24, 2007. 27-32.
■ 姚天昉,娄德成. 汉语语句主题语义倾向分析方法的研究. 全国第九届计算语言学联合学术会议(JSCL-2007)论文集,大连,2007年8月. 582-587.
■ 娄德成,姚天昉. 汉语句子语义极性分析和观点抽取方法的研究. 计算机应用. 第26卷, 第11期. 2006年11月. 2622-2625.
■ 姚天昉,聂青阳,李建超,李林琳,娄德成,陈珂,付宇. 一个用于汉语汽车评论的意见挖掘系统. 见:曹右琦,孙茂松主编,中文信息处理前沿进展-中国中文信息学会二十五周年学术会议论文集. 清华大学出版社,北京,2006年11月. 260-281.


Information Extraction and Information Retrieval
■ Tianfang Yao and Jianchao Li. A Token-based Online Web-Snippet Clustering Approach based on Directed Probability Graph. Journal of Computational Information Systems, Vol. 5, No. 3, 2009. pp 1235-1244.
■ Tianfang Yao and Jianchao Li. A Token-based Online Web-Snippet Clustering Approach based on Directed Probability Graph. Proc. of NCIRCS’2008(The 2nd Vol.). Beijing, Nov. 2008. pp 194-204.
■ Jian Zhang and Tianfang Yao. A Study of the Identification of Authorship for Chinese Texts. In Proc. of the 2008 IEEE International Conference on Intelligence and Security Informatics, Taibei, Taiwan. June 17-20, 2008. pp 263-264.
■ Tianfang Yao and Hans Uszkoreit. Building a Lexical Sports Ontology for Chinese IE Using Reusable Strategy. In the Proceeding of the 4th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD'07), Haikou, China. 2007.
■ Tianfang Yao and Hans Uszkoreit. Identifying Semantic Relations between Named Entities from Chinese Texts. In Ruqian Lu, J?rg H. Siekmann and Carsten Ullrich (Eds.): Cognitive Systems. LNAI 4429. Springer-Verlag, Berlin, Germany. 2007.
■ Li Jianchao and Yao Tianfang. An Efficient Token-based Approach for Web-Snippet Clustering. The 2nd International Conference on Semantics, Knowledge and Grid (SKG2006). Nov., 2006. 
Tianfang Yao and Hans Uszkoreit. Chinese Named Entity and Relation Identification System. In Proc. Of the Interactive Presentation Sessions (COLING-ACL 2006 IP), Sydney, Australia. July 2006. 
■ Tianfang Yao. Automatically Constructing Finite State Cascades for Chinese Named Entity Identification. In Günter Hommel and Sheng Huanye (Eds.): Human Interaction with Machines. Kluwer Academic Publishers. Dordrecht, The Netherlands. 2006. 
■ 王睿,张洁,张由仪,于禛,姚天昉. 基于混合模型的中文命名实体抽取系统的研究与实现. 清华大学学报,第45卷,第S1期,北京,2005年9月. 
■ 姚天昉. 一种用于汉语信息抽取的词汇本体. 全国第八届计算语言学联合学术会议(JSCL-2005)论文集,南京,2005年8月. 
■ Tianfang Yao and Hans Uszkoreit. A Novel Machine Learning Approach for the Identification of Named Entity Relations. In Proc. Of the Workshop on Feature Engineering for Machine Learning in Natural Language Processing (ACL 2005 Workshop), Michigan, USA, June 2005. 
■ 王睿,姚天昉. 基于实体语义关系的中文问题-答案关系研究. 第一届全国信息检索与内容安全学术会议论文集,上海,2004年11月. 
■ 郝玮,方欣,姚天昉. 句法规则的自动生成. 第一届全国信息检索与内容安全学术会议论文集,上海,2004年11月. 
■ Tianfang Yao. Hybrid Approach based Chinese Named Entity Extraction on a Specific Domain. In Proc. Of International Workshop ILT&CIP 2001 on Innovative Language Technology and Chinese Information Processing. Science Press, Beijing, China, 2004. 
■ Tianfang Yao, Wei Ding and Gregor Erbach. CHINERS: A Chinese Named Entity Recognition System for the Sports Domain. In Proc. Of the Second SIGHAN Workshop on Chinese Language Processing (ACL 2003 Workshop), Sapporo, Japan, July 2003. 
■ Tianfang Yao, Wei Ding and Gregor Erbach. Repairing Errors for Chinese Word Segmentation and Part-of-Speech Tagging. In Proc. Of the First International Conference on Machine Learning and Cybernetics 2002 (ICMLC 2002) , Beijing, China, Nov. 2002. 
■ Tianfang Yao, Wei Ding and Gregor Erbach. Correcting Word Segmentation and Part-Of-Speech Tagging Errors for Chinese Named Entity Recognition. In Günter Hommel and Sheng Huanye (Eds.): The Internet Challenge: Technology and Applications. Kluwer Academic Publishers. Dordrecht, The Netherlands. Oct. 2002. 
■ 尹凌, 姚天昉, 张冬茉, 李芳. 一种基于混合分析的汉语文本句法语义分析方法. 中文信息学报, 第16卷第四期. 2002年 7月. 
■ 姚天昉, 徐飞玉, 张冬茉, 李芳, 王纤, 盛焕烨. 一种基于信息抽取和文本生成的多语种信息检索模型. 2001年第一届中文信息处理和开发国际研讨会论文集. 高科技通讯(专辑), 2001年8月. 
■ Tianfang Yao. Hybrid Approach based Chinese Named Entity Extraction on Specific Domain. In Proc. Of International Workshop ILT&CIP 2001 on Innovative Language Technology and Chinese Information Processing. Science Press, Beijing, China. 2004.
WISCOM Data Service Platform
This project is financially supported by Shanghai Wiscom Info-Tech Co. Ltd. Its research period is from Dec. 2011 to Apr. 2012. The research contents of this project are: (1) Classification and Clustering for Mass Information; (2) Duplicated Content Elimination for Mass Information; (3) Purification for Mass Information; (4) Identification and Tracking for Hot and Sensitive Topics; (5) Orientation Analysis for Mass Information; (6) Trend Analysis; (7) Statistical Reports; (8) Mass Keywords Extraction; (9) Crisis Warning; (10) Intelligent Editing for Mass Information.
Role: Project leader


Research on the Application of Time-space based Chinese Information Retrieval Model
This project is financially supported by Shen Zhou Tu Ji Geographical Name Information Technology Co., Ltd. Its research period is from Jun. 2011 to Dec. 2011. The research contents of this project are: (1) Automatic Acquiring POI Extended Information from Web and Automatic Semantically Analyzing them; (2) Automatic Acquiring Time-space based Geographical names from Web and Automatic Semantically Analyzing them; (3) Building a Time-space based Information Retrieval Model; (4) Developing a Prototype System based on Time-space Information Retrieval model.
Role: Project leader


Research on the Application of Cultural Entity and Relationship for National Geographical Names
This project is financially supported by Shen Zhou Tu Ji Geographical Name Information Technology Co., Ltd. Its research period is from Jun. 2010 to Jun. 2011. The research contents of this project are: (1) Automatic Identification for Chinese Ancient and Current geographical Names and their Relations; (2) Automatic Matching between Chinese Ancient and Current Geographical Names and Address Codes; (3) Classification Architecture and Ontology for Chinese Ancient and Current Geographical Names and Cultural Achievement; (4) Automatic Acquire Cultural Achievement Information related to Ancient and Current Geographical Names on Web; (5) Information Index Primitive Model and Individual Query Model; (6) Database, Information Retrieval API and Individual Query System.
Role: Project leader


Research on Fine-grained Opinion Mining for Chinese Texts
This is a project from the National Natural Science Foundation of China (NSFC). Its research period is three years (Jan. 2008 - Dec. 2010). Opinion Mining for subjective texts is a novel and very important research direction. The research contents of this project are: (1) Annotation for Chinese opinioned subjective texts; (2) Automatic classification of Chinese opinioned subjective texts; (3) Identification of the topics of Chinese opinioned sentences; (4) Analysis of the sentiments for Chinese opinioned sentences; and (5) Identification of the relations between topics and sentiments for Chinese opinioned sentences.
The research work aims at resolving the problems concerning the identification of topics, sentiments and the relations between them in single sentences of Chinese opinioned subjective texts. Based on the theories of Computational Linguistics and Artificial Intelligence, a fine-grained opinion mining approach which is suitable to Chinese opinioned subjective texts will be proposed and implemented. The adopted approach utilizes the synthesized advantages of statistical and NLP methods in order to mine useful fine-grained information and knowledge to the maximun extent.
This language technology can be used not only for other natural language processing systems (applications), such as text categorization, text filtering, automatic summarization, natural language generation, question-answering system, dialogue system, machine translation; but also in many areas of daily life, such as e-commerce, e-learning, business intelligence, newspaper editor, business management, information control, public opinion surveys, etc
Role: Project leader


COLLATE (Computational Linguistics and Language Technology for Real Life Applications)
This is a BMBF, Germany funded project that supports the building of a German Competence Center for Language Technology in Saarbrücken. Involved partners are various departements at the University of the Saarland and at the German Research Center for Artificial Intelligence GmbH (DFKI, main coordinator). On the University side the basic research will be concerned mainly with three central application scenarios for language technology and will strongly support the transfer of new methods from academia into real world applications. The three topics are (1) the goal-oriented extraction of information from huge sets of digital documents, (2) the life-like interaction with information services and (3) the management of a large set of information through improved search and summarization techniques. The competence center as such will consist in three components, which will be coordinated at DFKI: (1) a virtual information center, (2) a demonstration center und (3) a evaluation center. The project will be jointly directed by Prof. Dr. H. Uszkoreit, Prof. Dr. M. Pinkal und Prof. Dr. Wolfgang Wahlster. The research period is from April 2001 to Dec. 2003.
Role: Project member


Research on Information Extraction and Template Generation based multilingual Information Retrieval
This project is financially supported by the National Natural Science Foundation of China. The research period is three years (Jan. 2001 - Dec. 2003).
Role: Project coordinator


Research on the Multilingual Text Generation Model for Natural Language
This project is financially supported by the National Natural Science Foundation of China. The research period is three years (Jan. 1997 - Dec. 1999).
Role: Project leader

联系我们 webmaster@cs.sjtu.edu.cn

上海交通大学计算机科学与工程系版权所有 @ 2013