A Multi-Document Multi-Lingual Automatic Summarization System

Abstract. In this paper, a new multidocument multi-lingual text summarization technique, based on singular value decomposition and hierarchical clustering, is proposed. The proposed approach relies on only two resources for any language: a word segmentation system and a dictionary of words along with their document frequencies. The summarizer initially takes a collection of related documents, and transforms them into a matrix; it then applies singular value decomposition to the resulted matrix. After using a binary hierarchical clustering algorithm, the most important sentences of the most important clusters form the summary. The appropriate place of each chosen sentence is determined by a novel technique. The system has been successfully tested on summarizIn this paper, a new multidocument multi-lingual text summarization technique, based on singular value decomposition and hierarchical clustering, is proposed. The proposed approach relies on only two resources for any language: a word segmentation system and a dictionary of words along with their document frequencies. The summarizer initially takes a collection of related documents, and transforms them into a matrix; it then applies singular value decomposition to the resulted matrix. After using a binary hierarchical clustering algorithm, the most important sentences of the most important clusters form the summary. The appropriate place of each chosen sentence is determined by a novel technique. The system has been successfully tested on summarizing several Persian document collections.