A Hybrid Model of Latent Semantic Analysis with Graph-Based Text Summarization on Telugu Text

Abstract

AbstractIn this paper, we are proposing a hybrid model of latent semantic analysis with graph-based xtractive text summarization on Telugu text. Latent semantic analysis (LSA) is an unsupervised method for extracting and representing the contextual-usage meaning of words by statistical computations applied to a corpus of text. Text rank algorithm is one of the graph-based ranking algorithm which is based on the similarity scores of the sentences. This hybrid method has been implemented on Eenadu Telugu e-news data. The ROUGE-1 measures are used to evaluate the summaries of proposed model and human-generated summaries in this extractive text summarization. The proposed LSA with Text rank method has a F1-score of 0.97 as against the F1-score of 0.50 for LSA and 0.49 of Text rank methods. The hybrid model yields better performance compared with the individual algorithms of latent semantic analysis and Text rank results.KeywordsText summarizationLatent semantic analysisText rank algorithmSingular value decompositionTelugu language