Fudan University at DUC 2005
نویسندگان
چکیده
In this paper, we described our participation in the question-focused multi-document summarization task of DUC 2005. Our system was based on a supervised machine learning method in which feature extraction was an important issue. We present the whole procedure of our system, focusing on the features we used. We also analyze the results of manual and automatic evaluations.
منابع مشابه
Fudan University at DUC 2006
This paper describes our work in query-based multi-document summarization task in DUC2006. We present the system overview, focusing on the newly developed techniques, including a new method of sentence similarity calculation, and application of anaphoric resolution to improve the readability of the summary. Evaluation results from NIST are also given and analyzed.
متن کاملThe Hong Kong Polytechnic University at DUC2005
This paper discusses the query-based multidocument summarization techniques implemented by the Hong Kong Polytechnic University at DUC 2005. The summarization system is built under the framework of MEAD. In addition to borrow the features provided by MEAD for text summarization, including centroid and sentence length etc., we also introduce the entity-based, pattern-based, termbased and semanti...
متن کاملA CrowdService: Optimizing Mobile Crowdsourcing and Service Composition
XIN PENG, School of Computer Science, Fudan University, China; Shanghai Key Laboratory of Data Science, Fudan University, China JINGXIAO GU, School of Computer Science, Fudan University, China; Shanghai Key Laboratory of Data Science, Fudan University, China TIAN HUAT TAN, Acronis, Singapore JUN SUN, Singapore University of Technology and Design, Singapore YIJUN YU, Department of Computing and ...
متن کاملFrom Definitions to Complex Topics : Columbia University at DUC 2005
We describe our work in adapting a system designed to answer definitional and biographical questions (i.e. “What/Who is X?”) to the topic-focused summarization task of DUC 2005. We present a system overview, focusing on newly developed aspects. We evaluate our performance, examining example output and analyzing our scores on the various metrics provided by NIST. We conclude with general observa...
متن کاملActive Targeting Liposomes: Promising Approach for Tumor-Targeted Therapy
Xiaoyi Wang1 and Weiyue Lu1-3* 1Department of Pharmaceutics, School of Pharmacy, Fudan University & Key Laboratory of Smart Drug Delivery (Fudan University), Ministry of Education, Shanghai 201203, PR China 2State Key Laboratory of Medical Neurobiology, The Collaborative Innovation Center for Brain Science, Fudan University, Shanghai 200032, PR China 3State Key Laboratory of Molecular Engineeri...
متن کامل