Ting Liu
|
A
vice dean and full professor of the School of Computer Science, Harbin
Institute of Technology, P. R. China. |
|
|
Director
of |
|
|
He is
interested in Information Retrieval and Natural Language Processing |
Contact information
Homepage:
http://ir.hit.edu.cn/~tliu
E-mail:
tliu@ir.hit.edu.cn
P.Box 321, Harbin Institute of Technology,
Tel: +86-451-86413683(86402993)-801
Fax: +86-451-86413683(86402993)-812
Academic Degrees
D. Sc. Computer Application
Technology
Dept.
of
Computer Science and Engineering
Harbin Institute of
Technology, P. R. China
1995.9 - 1998.7
Advisor: Prof. Jiarong Hong and Prof. Kaizhu
Wang
M.
Eng. Computer Applications
Dept. of Computer Science and Engineering
Harbin Institute of
Technology, P. R. China
1993.9 - 1995.7
Advisor: Prof. Kaizhu Wang
B.
Eng. Computer
Applications
Dept.
of Computer Science and Engineering
Harbin Institute of
Technology, P. R. China
1989.9 - 1993.7
Graduated with honors
RESEARCH AREAS
TEACHING EXPERIENCE
1995 - 1998: “Artificial Intelligence”,
for graduate students of computer science, Harbin Institute of Technology,
2001 - 2004: “Statistical Natural
Language Processing”, for graduate students of computer science, Harbin
Institute of Technology,
2001 - 2008: “Information
Retrieval”, for graduate students of computer science, Harbin Institute of
Technology,
Professional
experience
2004.7 - present: Professor, Harbin Institute of Technology,
2000.10 -
2004.7: Associate Professor, Harbin
Institute of Technology,
2000.5 -
2000.10: Lecturer,
Harbin Institute of Technology,
1999.4 -
2000.5: Associate
Researcher, Natural Language Computing Group, Microsoft Research
1998.7 -
1999.4: Lecturer,
Dept. of Computer Science and Engineering, Harbin Institute of Technology
1995.6 -
1998.7: Teaching
Assistant, Dept. of Computer Science and Engineering, Harbin Institute of
Technology
1995.9 -
1998.7: Ph.D student, Dept. of Computer Science and Engineering,
Harbin
1993.9 -
1995.7: Graduate
student, Harbin Institute of Technology,
1989.9 -
1993.7: Undergraduate
student, Harbin Institute of Technology,
Research Grants:
Government
Projects:
2009.1 - 2011.12: Chinese Dependency
Parsing, National Natural Science Foundation of
2007.1 - 2009.12: Chinese Semantic
Role Labeling, National Natural Science Foundation of
2007.1 - 2008.12: XML-Based Multilevel Integrated Language Technology
Platform, National High Technology R&D Program (863 Program)
2006.1 - 2008.12: Equivalent
Pseudo-Word Based Chinese Unsupervised Word Sense Disambiguation, National
Natural Science Foundation of
2006.1 - 2008.12: Phrase and Simple
Sentence Paraphrasing Technology, National Natural
Science Foundation of
2005.1 - 2008.12: Question Understanding and Answer Extraction, Sub-Project of Theory and
Method of Question-Answering (Key Project of National Natural Science Foundation of
2003.1 - 2004.12: Open-domain Question Answering, National Natural Science Foundation of China
2003.2 - 2003.7: Chinese Information Fuzzy Matching Technology, National High Technology R&D Program (863 Program)
2001.1 - 2002.12: Chinese Automatic Proofreading System Based on Dependency Parsing, National High Technology R&D Program (863 Program)
university
Administration and Local community services
·
2009.3 - present, Assistant Dean of
·
2009.9 - present, Director of Center for
Information Retrieval
Membership in
professional organizations
ACL member
Chinese Information Processing Society (CIPS)
o Council member
o Vice director of
Information Retrieval Committee
o Member of
Computational Linguistics Committee
CCF (Chinese Computer Federation)
o Senior Member
o Chinese Information
Technology Committee, member
o Young Computer
Scientists & Engineers Forum(YOCSEF), Vice Chair
Professional
Activities
Papers in English
2011:
l
Zhenghua Li, Min Zhang, Wanxiang
Che, Ting Liu, Wenliang
Chen, Haizhou Li. Joint Models for Chinese POS
Tagging and Dependency Parsing. In Proceedings of EMNLP 2011. 2011.07,
pp1180-1191, Edinburgh, Scotland, UK.
l
Wei
Song, Yubin Xie, Yu Zhang,
Ting Liu, Sheng Li. Query Term Ranking based on
Search Results Overlap. To appear in Proceedings of the 34th ACM SIGIR
Conference.
2010:
l
Wanxiang Che, Ting Liu, Yongqiang Li. Improving Semantic Role Labeling with Word Sense.
In Proceedings of the Human Language Technologies: The 2010 Annual Conference
of the North American Chapter of the Association for Computational Linguistics
(NAACL2010). 2010.06, pp246-249, Los Angeles, California.
l
Wanxiang Che, Ting Liu.
Using Word Sense Disambiguation for Semantic Role Labeling. In Proceedings of
the 4th International Universal Communication Symposium (IUCS 2010). 2010.10,
pp166-173, Beijing, China.
l
Wanxiang Che, Ting Liu.
Jointly Modeling WSD and SRL with Markov Logic. In Proceedings of the 23rd
International Conference on Computational Linguistics (Coling
2010). 2010.08, pp161-169, Beijing, China.
l
Wanxiang Che, Zhenghua Li, Ting Liu. LTP: A Chinese Language Technology
Platform. In Proceedings of the Coling 2010:
Demonstrations. 2010.08, pp13-16, Beijing, China.
l
Shiqi Zhao, Haifeng
Wang, and Ting Liu. Paraphrasing with Search Engine Query Logs. Proceedings of
the 23rd International Conference on Computational Linguistics (Coling 2010), pages 1317–1325, Beijing, August 2010
l
Shiqi Zhao, Haifeng
Wang, Xiang Lan, and Ting
Liu. Leveraging Multiple MT Engines for Paraphrase Generation. Proceedings of
the 23rd International Conference on Computational Linguistics (Coling 2010), pages 1326–1334, Beijing, August 2010
l
Yanyan Zhao, Bing Qin and Ting Liu. Integrating
Intra- and Inter- Document Evidences for Improving Sentence Sentiment
Classification. ACTA AUTOMATICA SINICA. 2010,36(10):1417-1425.
l
Yanyan Zhao, Bing Qin and Ting Liu. Appraisal
Expression Recognition with Syntactic Path for Sentence Sentiment
Classification. International Journal of Computer Processing of Oriental
Languages. 2011,23(1):21-37.
l
Yanyan Zhao, Bing Qin, Shen
Hu, Ting Liu. Generalizing Syntactic Structures for
Product Attribute Candidate Extraction. The 2010 Annual Conference of the North
American Chapter of the Association for Computational Linguistics. 2010,
pp377-380
l
Yuhang Guo, Wanxiang Che, Wei He, Ting Liu, Sheng Li. HIT-CIR: An Unsupervised
WSD System Based on Domain Most Frequent Sense Estimation. Proceedings of the
5th International Workshop on Semantic Evaluation, ACL 2010, pages 407–410
l
Zhichang Zhang, Yu Zhang, Ting Liu, Sheng Li. Automatic Recognition of Focus and Interrogative
Word in Chinese Question for Classification. In Proceedings of the Coling 2010: Demonstrations. 2010.08, pp13-16, Beijing,
China.
l
QIN
Bing,ZHAO Yanyan,DING Xiao. Event Type Recognition Based on Trigger
Expansion. TSINGHUA SCIENCE AND TECHNOLOGY ISSNll1007-0214ll01/17llpp251-258
Volume 15, Number 3, June 2010
l
Zhenghua Li, Wanxiang Che, Ting Liu. Improving Dependency Parsing Using
Punctuation. International Conference on Asian Language Processing(IALP)
2010.
l
Wei
Song ,Yu Zhang ,Ting Liu and Sheng
Li. Bridging Topic Modeling and Personalized Search. Coling
2010: Posters 1167--1175
l
Fikadu Gemechu, Zhang Yu
and Liu Ting. A Framework for Personalized Information Retrieval Model.
International Conference on Systems Engineering and Modeling, April 23-25,
2010, Bangkok, Thailand.
l
Dayong Wu, Yu Zhang, Shiqi
Zhao, Ting Liu. Identification of Web Query Intent Based on Query Text and Web
Knowledge. the Pervasive Computing, Signal Processing
and Applications (PCSPA-2010). 2010. (EI Indexed).
2009:
l Shiqi Zhao, Xiang Lan, Ting Liu, and Sheng Li. 2009. Application-driven Statistical Paraphrase Generation. In Proceedings of ACL-IJCNLP. pp.834-842. August 2-7, 2009. Singapore.
l
l Shiqi Zhao, Haifeng Wang, Ting Liu, Sheng Li. Extracting Paraphrase Patterns from Bilingual Parallel Corpora. To Appear in Journal of Natural Language Engineering (JNLE).
l Wanxiang Che, Zhenghua Li, Yongqiang Li, Yuhang Guo, Bing Qin, Ting Liu. 2009. Multilingual Dependency-based Syntactic and Semantic Parsing. In Proceedings of CoNLL-2009. pp.49-54. June 4-5, 2009. Boulder, Colorado, U.S.
2008:
l
Shiqi Zhao, HaifengWang, Ting Liu, Sheng Li.
2008. Pivot Approach for Extracting
Paraphrase Patterns from Bilingual Corpora. In Proceedings of ACL-08:
HLT. pp.780–788. June 16-18, 2008.
l
Shiqi Zhao, Cheng Niu, Ming Zhou, Ting Liu, Sheng
Li. 2008. Combining Multiple Resources
to Improve SMT-based Paraphrasing Model. In Proceedings of ACL-08: HLT. pp.1021–1029. June 16-18, 2008.
l
Xiaofeng Yang, Jian Su, Jun Lang,
ChewLim Tan, Ting Liu, Sheng Li. 2008. An Entity-Mention Model for Coreference
Resolution with Inductive Logic Programming. In Proceeding of ACL-08: HLT. pp.843-851. June 16-18, 2008.
l
Wanxiang Che, Min Zhang, Ai Ti Aw, Chew Lim Tan, Ting
Liu, Sheng Li. 2008. Fast Computing Grammar-driven Convolution Tree Kernel for Semantic Role
Labeling. In Proceedings of IJCNLP. pp.781-786.
January 7-12, 2008.
l
Wanxiang Che, Zhenghua Li, Yuxuan Hu, Yongqiang
Li, Bing Qin, Ting Liu, and Sheng Li. 2008. A Cascaded Syntactic and Semantic Dependency
Parsing System. In Proceedings of the Twelfth Conference on
Computational Natural Language Learning (Conll-2008). pp.238-242.
August 16-17, 2008.
l
Ruifang He, Yang Liu, Bing Qin, Ting Liu, Sheng Li. 2008. HITIR’s Update Summary at TAC2008:
Extractive Content Selection for Language Independence. In Proceedings of
TAC2008 Workshop. November 17-19, 2008.
l
Wei Zheng, Yu Zhang, Yu Hong, Jili
Fan, Ting Liu. 2008. Topic Tracking Based on
Keywords Dependency Profile. In Proceeding os AIRS2008. pp.129-140. January 16-18, 2008.
l
Bing Qin, Yanyan Zhao, Leilei Gao,
Ting Liu. Recommended or Not Give advice on Online Product. In Proceedings of Fifth
international conference on Fuzzy Systems and Knowledge Discovery. pp.208-212. October 18-20, 2008.
l
Min Zhang, Wanxiang Che, Guodong Zhou, Ai Ti Aw, Chew
Lim Tan, Ting Liu, and Sheng Li. Semantic Role Labeling Using a Grammar-Driven
Convolution Tree Kernel. IEEE Transactions on Audio, Speech, and
Language Processing. 2008, 16(7):1315-1329 (SCI Impact Factor: 0.8)
2007:
l
Min Zhang, Wanxiang Che, Ai Ti Aw, Chew Lim Tan, Guodong Zhou, Ting Liu, Sheng Li.
2007. A Grammar-driven Convolution Tree
Kernel for Semantic Role Classification. In Proceedings of ACL. pp.200-207. June 23-30, 2007.
l
Shiqi Zhao, Ming
Zhou, Ting Liu. 2007. Learning Question
Paraphrases for QA from Encarta Logs. In Proceedings of IJCAI-07. pp.1795-1800. January 6-12, 2007.
l
Shiqi Zhao, Ting
Liu, Xincheng Yuan, Sheng
Li, and Yu Zhang. 2007. Automatic
Acquisition of Context-Specific Lexical Paraphrases. In Proceedings of IJCAI-07.
pp.1789-1794. January 6-12, 2007.
l
Yuhang Guo, Wanxiang Che,
Yuxuan Hu, Wei Zhang, Ting
Liu. 2007. HIT-IR-WSD: A WSD System for
English Lexical Sample Task. In Proceedings of SemEval.
pp.165-168. June 23-24, 2007.
l
Shiqi Zhao, Lin
Zhao, Yu Zhang, Ting Liu, Sheng Li. 2007. HIT:Web based Scoring Method for English Lexical
Substitution. In Proceedings of SemEval. pp.173-176. June 23-24, 2007.
l
Jun Lang, Bing Qin, Ting Liu, Sheng
Li. Intra-document Coreference
Resolution: The State of the Art. Journal of Chinese Language and
Computing, 2007,17(4):227-253.
l
Liu Ting, Ma Jinshan, Zhang Huipeng, Li Sheng. Subdividing Verbs to Improve
Syntactic Parsing. Journal of Electronics (
2006:
l
Zhimao Lu, Haifeng Wang, Jianmin Yao, Ting Liu, Sheng Li.
2006. An Equivalent Pseudoword Solution to Chinese
Word Sense Disambiguation. In Proceedings of ACL. pp.457-464.
July 17-21.
l
Wanxiang
Che, Min Zhang, Ting Liu, Sheng Li. 2006. A Hybrid Convolution
Tree Kernel for Semantic Role Labeling. In Proceedings of ACL. pp.73-80. July 17-21.
l
Liqi Gao,
Yu Zhang, Ting Liu, Guiping Liu. 2006. Word Sense
Language Model for Information Retrieval. In Proceedings of AIRS. pp.158-171. October 16-18.
l
Shiqi Zhao, Ting Liu, Xincheng
Yuan, Sheng Li, Yu Zhang. 2006. Web Mining for
Lexical Context-Specific Paraphrasing. In Proceedings of AIRS. pp.673-679. October 16-18.
l
Ting Liu, Jinshan Ma, Sheng Li. Building a Dependency Treebank for Improving
Chinese Parser. Journal of Chinese Language and Computing, 2006,16(4):207-224.
l
Ting Liu, Jinshan Ma, Huijia Zhu,
Sheng Li, 2006. Dependency Parsing Based on
Dynamic Local Optimization. In Proceedings of CoNLL. pp.211-215. June 8-9.
2005:
l
Qin Bing, Liu Ting, Li Sheng. Summarization Based on Physical Features and
Logical Structure of Multi Documents. High Technology Letters, 2005,11(2):133-136.
l
Qin Bing, Liu Ting, Zhang Yu, Li Sheng.
Research on Multi-Document Summarization
Based on Latent Semantic Indexing. Journal of Harbin Institute of
Technology, 2005,12(1):91-94.
l
Zhuoran Wang, Ting
Liu. Chinese Unknown Word
Identification Based on Local Bigram Model. International Journal of
Computer Processing of Oriental Languages. 2005,18(3):185-196.
l
Ting Liu, Zhimao Lu, Sheng Li. Chinese
Word sense disambiguation based on Neural Networks. Journal of Harbin
Institute of Technology, 2005,12(4):408-417.
l
Ting Liu, Wanxiang Che, Sheng Li, Yuxuan Hu, Huaijun
Liu. 2005. Semantic role labeling
system using maximum entropy classifier. In Proceedings of CoNLL. pp.189-192. June 29-30,
2005.
l
Weigang Li, Ting
Liu, Yu Zhang, Sheng Li,
l
Wanxiang Che, Jianmin Jiang, Zhong Su, Yue Pan, Ting Liu.
2005. Improved-Edit-Distance Kernel for
Chinese Relation Extraction. In Proceedings of The Second International
Joint Conference on Natural Language Processing (IJCNLP-05), pp.134-139.
October 11-13.
l
Huipeng Zhang, Ting Liu, Jinshan Ma,
Xiantao Liao. 2005. Chinese Word Segmentation with
Multiple Postprocessors in HIT-IRLab. In
Proceedings of SIGHAN, pp.172-175. October 14-15.
l
Gao Liqi, Liu Ting, Chen Ru, Zhang
Yu. 2005. Thesaurus-Based Semantic
Smoothing in Language Modeling for Chinese Document Retrieval. In
Proceedings of International Conference on Multilingual Information Processing.
pp.319-323.
l
He Ruifang, Qin Bing, Liu Ting,
Li Sheng. 2005. The Topic Detection and Tracking with Topic Sensitive Language Model.
In Proceedings of International Conference on Multilingual Information
Processing. pp.324-327.
l
Lu Zhimao, Liu Ting, Li Sheng. 2005. Unsupervised
Chinese Word Sense Disambiguation Based on Equivalent Pseudowords.
In Proceedings of International Conference of Chinese Computing.
2004:
l
Weigang Li, Ting Liu, Sheng Li. 2004.
Combining Sentence Length with Location Information
to Align Monolingual Parallel Texts. In Proceedings of AIRS. pp.71-77. October 18-20,
2004.
l
Jinshan Ma, Yu Zhang, Ting Liu,
Sheng Li. 2004. A Statistical Dependency Parser
of Chinese under Small Training Data. In Proceedings of The 1st International Joint
Conference of Natural Language Processing. pp.1-4. March 22-24, 2004.
l
Zhuoran Wang, Ting
Liu. 2004. Chinese Unknown Word
Identification Based on Local Bi-gram Model with Integrally Smoothing
Assumption. In Proceedings of International Conference on Chinese
Language Computing. .
l
Yanqiu Shao, Jiqing Han, Ting Liu, Yongzhen Zhao. 2004. Prosodic Words Boundaries Prediction for Mandarin Text-to-speech.
.
l
Weigang Li, Ting Liu, Zheng
Wang, Sheng Li. 2004. Aligning Bilingual Corpora
Using Sentences Location Information. In Proceedings of Third SIGHAN Workshop
on Chinese Language Processing. pp.141-147. July
25-26, 2004.
l
Zhimao Lu, Ting
Liu, Sheng Li. Combining Neural Networks and Statistics for Chinese Word Sense
Disambiguation. In Proceedings of Third SIGHAN Workshop on Chinese
Language Processing. pp.49-56. July 25-26, 2004.
l
Wanxiang Che, Ting Liu, Sheng Li. A New Chinese Natural Language Understanding
Architecture Based on Multilayer Search Mechanism. In Proceedings of
Third SIGHAN Workshop on Chinese Language Processing. pp.134-140.
July 25-26, 2004.
PUBLICATIONS in
Chinese
2011年:
l 赵妍妍, 秦兵, 车万翔, 刘挺. 基于句法路径的情感评价单元识别.
软件学报.
2011,22(5):887-898.
2010年:
l 赵世奇,赵琳,刘挺,李生. 基于二元分类的复述搭配抽取.
软件学报,
Vol.21, No.6, June 2010, pp.1267-1276
l 张宇,宋巍,谢毓彬,高汉东,刘挺,李生.
利用URL类别改进查询主题分类. 第六届全国信息检索学术会议pp157-166,中国牡丹江
l 张伟男,张宇,刘挺. 基于中心理论的中文对话省略恢复研究.
第六届全国信息检索学术会议
pp307-315,2010年8月,中国牡丹江
l 伍大勇,张宇,刘挺. 中文交互式问答用户问题相关检测研究.
中文信息学报.
Vol. 24. No.3. 2010. 5. pp. 11-18.
l 付瑞吉,秦兵,刘挺. 面向音乐领域的文本检索与挖掘系统.
第五届全国青年计算语言学研讨会(YWCL
2010),
pp:424-430。2010年10月,中国武汉
l 丁效,宋凡,秦兵,刘挺.
音乐领域典型事件抽取方法研究.
第五届全国青年计算语言学研讨会(YWCL
2010), 2010, 7: 431-437
l 李正华, 车万翔, 刘挺. 基于 XML 的语言技术平台. 第五届全国青年计算语言学研讨会(YWCL)
2010
l 李正华,车万翔,刘挺. 基于柱状搜索的高阶依存句法分析.
中文信息学报.
2010, 24(1):37-41
l 张志昌,张宇,刘挺,李生.
基于话题和修辞识别的阅读理解why型问题问答. 计算机研究与发展. 2010,42(12).
l 宋巍,张宇,刘挺,李生.
基于检索历史上下文的个性化查询重构技术研究.
第六届全国信息检索会议,CCIR2010.
l 伍大勇,赵世奇,刘挺,张宇.
融合多类特征的Web查询意图识别. 第六届全国信息检索学术会议(CCIR
2010).
2009年:
l 赵世奇, 张宇, 赵琳, 刘挺, 李生. 基于网络挖掘的上下文相关词汇级复述研究.
软件学报,
2009,20(7):1746-1755.
l 赵世奇, 刘挺, 李生. 复述技术研究. 软件学报, 2009,20(8):2124-2137.
l 贺瑞芳, 秦兵, 刘挺, 潘越群, 李生. 基于宏微观重要性判别模型的时序多文档文摘.
计算机研究与发展,
2009,46(7):1184-1191.
l 赵世奇, 刘挺, 李生. 基于自动构建语料库的词汇级复述研究.
电子学报,
2009,37(5):975-980.
l 张志昌, 张宇, 刘挺, 李生. 开放域问答技术进展. 电子学报,
2009,37(5):1058-1069.
l 张志昌, 张宇, 刘挺, 李生. 基于线索词识别和训练集扩展的中文问题分类.
高技术通讯,
2009,19(2):111-118.
l 张宇, 范基礼, 郑伟, 邹博伟, 刘挺. 基于人工标注的个性化检索系统评测的研究.
中文信息学报, 2009,23(2):62-69.
l 张宇, 赵鑫, 刘挺. 面向协作式问答的问题理解技术研究.
中文信息学报,
2009,23(2):28-33.
l 王丽杰,车万翔,刘挺. 基于SVMTool的中文词性标注. 中文信息学报,
2009,23(4):16-21.
l 李正华, 车万翔, 刘挺. 2009. 基于柱状搜索的高阶依存句法分析. 第十届全国计算语言学学术会议.
pp.117-122. 2009年7月, 烟台.
l 刘鸿宇, 赵妍妍, 秦兵, 刘挺. 2009. 评价对象抽取及其倾向性分析.
第十届计算语言学会议.
pp.612-617. 2009年7月, 烟台.
2008年:
l 郭宇航, 车万翔, 刘挺. 基于语言模型验证的词义消歧语料获取.
中文信息学报, 2008,22(6):38-42.
l 李正华, 车万翔, 刘挺. 短语结构树库向依存结构树库转化研究. 中文信息学报, 2008,22(6):14-19.
l 赵妍妍, 秦兵, 车万翔, 刘挺. 中文事件抽取技术研究. 中文信息学报,2008,22(1): 3-8.
l 宋巍, 秦兵,
l 洪宇, 张宇, 范基礼, 刘挺, 李生. 基于子话题分治匹配的新事件检测.
计算机学报, 2008,31(4):687-695.
l 洪宇, 张宇, 郑伟, 刘挺, 李生. 信息过滤中基于二元近似关系分布的噪声屏蔽算法.
软件学报,
2008,19(11):2887-2898.
l 洪宇, 张宇, 范基礼, 刘挺, 李生. 基于语义域语言模型的中文话题关联检测.
软件学报,
2008,19(9):2265-2275.
l 贺瑞芳, 秦兵, 潘越群, 刘挺, 李生. 基于启发式错误驱动学习的中文时间表达式识别.
高技术通讯,2008,18(12):1258-1262.
l 邹博伟, 张宇, 郑伟, 范基礼, 刘挺. 基于改进的TextTiling方法的用户新兴趣发现的研究.
第四届全国信息检索与内容安全学术会议.
pp.256-264. 2008年11月, 北京.
2007年:
l 刘挺, 车万翔, 李生. 基于最大熵分类器的语义角色标注.
软件学报,
2007,18(3):565-573.
l 李维刚, 刘挺, 李生. 基于双语语料库的短语复述实例获取研究.
中文信息学报,
2007,8(5):362-367.
l 洪宇, 张宇, 刘挺,
郑伟, 龚诚, 李生. 基于层次聚类的自适应信息过滤学习算法.
中文信息学报, 2007,21 (03):47-53.
l 刘怀军, 车万翔, 刘挺. 中文语义角色标注的特征工程.
中文信息学报, 2007,21(01):79-84.
l 赵世奇, 刘挺, 李生. 一种基于主题的文本聚类方法.
中文信息学报,
2007,21(2): 58-62.
l 贺瑞芳, 秦兵, 刘挺,
潘越群, 李生. 基于依存分析和错误驱动的中文时间表达式识别.
中文信息学报, 2007,21(05):36-40.
l 黄永光, 刘挺, 车万翔, 胡晓光. 面向变异短文本的快速聚类算法.
中文信息学报, 2007,21(2):63-68.
l 洪宇, 张宇, 刘挺, 李生. 话题检测与跟踪的评测及研究综述.
中文信息学报,
2007,21(6):71-87.
l 陈毅恒, 秦兵, 刘挺, 林建国, 李生. 2007. 基于错误预测的文本分类方法. 第九届全国计算语言学学术会议第九届全国计算语言学学术会议论文集.
l 郑伟, 张宇, 邹博伟, 洪宇, 刘挺. 2007. 基于相关性模型的中文话题跟踪研究.
全国第九届计算语言学学术会议.
l 张志昌, 张宇, 刘挺, 李生. 2007. 基于浅层语义树kernel 的阅读理解答案句抽取. 第三届全国信息检索与内容安全学术会议论文集.
pp.294-300. 2007年11月, 苏州.
2006:
l 秦兵, 刘挺, 陈尚林, 李生. 多文档文摘中句子优化选择方法研究.
计算机研究与发展,
2006,43(6):1129-1134.
l 文勖,
张宇, 刘挺,
马金山. 基于句法结构分析的中文问题分类.
中文信息学报, 2006,20(2):33-39.
l 刘挺, 李维刚, 张宇, 李生. 复述技术研究综述. 中文信息学报,
2006,40(4):25-33.
l 赵妍妍, 王啸吟, 秦兵, 车万翔, 刘挺. 2006. 中文事件抽取中事件类别的自动识别.
第三届全国学生计算语言学研讨会,
pp.240-245. 2006年8月, 沈阳.
2005:
l 张宇, 刘挺, 文勖.
基于改进贝叶斯模型的问题分类.
中文信息学报,
2005,19(2):100-105.
l 张宇, 刘挺, 陈毅恒, 赵世奇, 李生. 自然语言文本水印技术. 中文信息学报,
2005,19(6):13-20.
l 陈儒, 张宇, 刘挺. 面向中文特定信息变异的过滤技术研究.
高技术通讯,
2005,15(9):7-12.
l 车万翔, 刘挺, 李生. 实体关系自动抽取. 中文信息学报, 2005,19(2):1-6.
l 赵世奇, 张宇, 刘挺, 陈毅恒, 黄永光, 李生. 基于类别特征域的文本分类特征选择方法.
中文信息学报,
2005,19(6):21-27.
l 秦兵, 刘挺, 李生. 多文档自动文摘综述. 中文信息学报, 2005,19(6):
13-20.
l 卢志茂, 刘挺, 李生. 两种基于统计的汉语词义消歧模型.
哈工大学报专刊,
2005,37(7):119-122.
l 车万翔, 刘挺, 李生. 浅层语义分析. 2005. 全国第八届计算语言学联合学术会议,
pp.154-160. 2005年8月, 南京.
l 张宇, 刘挺, 高立琦, 车万翔, 朱传靖. 2005. 基于常问问题集的在线客服实验研究.
全国第八届计算语言学联合学术会议.
pp.474-480. 2005年8月, 南京.
l 赵妍妍, 秦兵, 刘挺, 张俐, 苏中. 2005. 基于多特征融合的句子相似度计算.
全国第八届计算语言学联合学术会议.
pp.168-174. 2005年8月, 南京.
l 文勖,
张宇,
刘挺.
2005. 类别主特征结合句法特征的中文问题层次分类. 第二届全国信息检索与内容安全学术会议.
pp.211-220. 2005年10月. 北京.
l 秦兵, 刘挺, 李生. 基于子主题的多文档文摘.
第二届全国信息检索与内容安全学术会议.
pp.365-371. 2005年10月. 北京.
l 张志昌, 张宇, 高立琦, 袁新成, 胡晓光, 刘挺, 李生. 2005. 哈尔滨工业大学信息检索研究室技术报告.
863信息检索评测研讨会.
2004:
l
卢志茂, 刘挺, 李生. 基于依存分析和贝叶斯网络的无指导汉语词义消歧. 高技术通讯, 2004(2):7-11.
l
车万翔, 刘挺, 秦兵, 李生. 基于改进编辑距离的中文相似句子检索. 高技术通讯, 2004(7):15-20.
l
赵永贞, 刘挺, 王志伟, 陈惠鹏, 邵艳秋. 汉语文语转换系统中停顿指数的自动标注. 中文信息学报, 2004(5):48-53.
l
秦兵, 刘挺, 李生. 基于局部主题判定与抽取的多文档文摘技术. 自动化学报, 2004(6):905-910.
l
卢志茂, 刘挺,
l
马金山, 张宇, 刘挺, 李生. 利用三元模型及依存分析查找中文文本错误. 情报学报, 2004(6):723-728.
l
廖先桃, 于海滨, 秦兵, 刘挺. 2004. HMM与规则相结合的中文命名实体识别方法研究. 第二届全国学生计算语言学研讨会.
l
张宇, 刘挺. 2004. 残缺邮件与完整邮件分离技术的研究. 全国网络与信息安全技术研讨会.
l
陈儒, 张宇, 刘挺. 2004. 面向网络实施数据流的中文信息多模式模糊匹配. 全国网络与信息安全技术研讨会.
l
秦兵, 刘挺, 高晔. 2004. 多文档集合逻辑主题的确定. 第一届全国信息检索与内容安全学术会议.
l
张宇, 刘挺, 文勖. 2004. 基于改进贝叶斯模型的问题分类. 第一届全国信息检索与内容安全学术会议.
l
车万翔, 刘挺, 李生. 2004. 实体关系的自动抽取. 第一届全国信息检索与内容安全学术会议.
Technology
Evaluation:
International evaluation:
1.
CoNLL’2009, Semantic Role Labeling and Dependency Parsing
task, won the 1st place among 19 systems
2.
CoNLL’2008, Semantic Role Labeling and Dependency Parsing
task, won the 2nd place among 20 systems
3.
NIST Machine Translation, 2008, English-Chinese
Translation, won the 5th place among 9 systems
4.
CoNLL’2006, Semantic Role Labeling task, won the 6th
place among 19 systems
5.
SIGHAN’2005, Chinese word segmentation task, won the 3rd
place
6.
2003, Won the 1st place in text summarization task
7.
2004, Won the 2nd place in text retrieval task
8.
2005, Won the 1st place in text retrieval task
TECHNOLOGY TRANSFER:
Cooperation with
Microsoft Research Asia,
1.
Chinese-English Bilingual
Example Sentence Retrieval has been transferred to “Kingsoft
- ICIBA” which is the biggest on-line bilingual dictionary and community in
China
2.
Chinese processing
technology package including 4 kinds of Chinese/English processing technologies has been
transferred to Kingsoft - WPS which is a Chinese
office software with more than 20 years history
3.
Language Technology
Platform (LTP) is an integrated Chinese analysis software platform. It includes 6 kinds of foundational core technologies,
such as word segmentation, POS tagging, word sense disambiguation, dependency
parsing, semantic role labeling, and 3 kinds of basic Chinese thesaurus and
corpora. So far, more than 300 research labs in the world have freely shared
LTP, and Huawei Corporation has paid for the right to
use it.
Demos
1.
Language Technology Platform: http://ir.hit.edu.cn/demo/ltp/
2.
Text Mining System: http://ir.hit.edu.cn/demo/tms/
3.
Google/Kingsoft Iciba Bilingual Example Sentence Retrieval: http://dj.iciba.com/
4.
Information Extraction for Organization : http://ir.hit.edu.cn/demo/oie/