Analysis of Sentence Scoring Methods for Extractive Automatic Text Summarization

Abstract

Automatic text summarization is a major area of research in the domain of information systems. Most of the methods requires domain knowledge in order to produce a coherent and meaningful summary. In Extractive text summarization, sentences are scored on some features. A large number of feature based scoring methods have been proposed for extractive automatic text summarization by researchers. This paper reviews features for sentence scoring. The results on combinations of various features for scoring are discussed. ROUGE-N is used to evaluate generated summary with abstractive summary of DUC 2002 dataset.