Paper: A Multi-Document Multi-Lingual Automatic Summarization System

ACL ID I08-2101
Title A Multi-Document Multi-Lingual Automatic Summarization System
Venue International Joint Conference on Natural Language Processing
Session Main Conference
Year 2008

Abstract. In this paper, a new multi- document multi-lingual text summarization technique, based on singular value decom- position and hierarchical clustering, is pro- posed. The proposed approach relies on only two resources for any language: a word segmentation system and a dictionary of words along with their document fre- quencies. The summarizer initially takes a collection of related documents, and trans- forms them into a matrix; it then applies singular value decomposition to the re- sulted matrix. After using a binary hierar- chical clustering algorithm, the most im- portant sentences of the most important clusters form the summary. The appropri- ate place of each chosen sentence is deter- mined by a novel technique. The system has been successfully tested on summariz- ...