JournalVolume 6, №2, Special Issue on Information Technologies and ApplicationsExperimental investigating the F-measure as similarity measure for automatic text summarization (pages 278-287) Rasim M. Alguliev and Ramiz M. Aliguliyev Abstract. This paper evaluates the performance of different similarity measures in the context of document summarization. For this purpose in this paper a simple and effective sentence extractive technique is used. The proposed method is based on evaluation of relevance score of sentence. Many measures are available for the calculation of inter sentence relationships. To calculate a similarity between sentences we use cosine measure and classical IR F-measure. We present a comprehensive experimental evaluation two different document collection. Our experimental results show that F-measure lead to the best overall results than cosine measure.
|
|