Title :
Chinese multi-document summarization based on Topic Detection technology
Author :
Mei-ling Liu ; Tie-Jun Zhao
Author_Institution :
Dept. of Comput. Sci. & Technol., Harbin Inst. of Technol., Harbin, China
Abstract :
This paper reports an initial study that aims to Chinese multi-document summarization. We introduce and compare different dynamic threshold model which TDT (Topic Detection and Tracking), and get document sets based on topic, then focus on Chinese multi-document summarization generation. Our approaches are based on the combination TDT temporal properties and multi-document summarization. Results show that using different dynamic threshold in TDT influence output summary representation. For our future work, we will continue to study the temporal multi-document summarization base on the web.
Keywords :
document handling; information analysis; information retrieval; natural language processing; Chinese multidocument summarization; TDT temporal property; dynamic threshold model; topic detection and tracking; topic detection technology; Abstracts; Application software; Broadcast technology; Broadcasting; Computational intelligence; Computer industry; Computer science; Detection algorithms; Natural language processing; Paper technology; Topic Detection; dynamic threshold; multi-document summarization; temporal properties;
Conference_Titel :
Computational Intelligence and Industrial Applications, 2009. PACIIA 2009. Asia-Pacific Conference on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-4606-3
DOI :
10.1109/PACIIA.2009.5406450
