Generic Text Summarization Using Local and Global Properties of Sentences
Canasai Kruengkrai and Chuleerat Jaruskulchai
Abstract
As the enormous amount of on-line text grows on the World-Wide Web, the development of methods for automatically summarizing this text becomes more important. In this paper, we propose an alternative approach for extracting the most salient sentences from the original document to form a summary. The idea of our approach is to exploit both the local and the global properties of sentences. The local property can be considered as clusters of significant words within each sentence, while the global property can be though of as relations of all sentences in a document. These two properties are combined for ranking and extracting summary sentences. Experimental results show that our approach achieves acceptable performance.
Download: pdf, ps
Canasai Kruengkrai