Implementation and Evaluation of Evolutionary Connectionist Approaches to Automated Text Summarization | Science Publications

Journal of Computer Science

Rajesh S. Prasad¹  Uday Kulkarni¹ 

关键词: Neural network;    feature extraction;    text summarization;    part of speech;    evolutionary connectionist;    semantic net;    perceptron neural network;    evolutionary programming;    chromosomes;    automatic text;    semantic nets;   

DOI  :  10.3844/jcssp.2010.1366.1376

学科分类：计算机科学（综合）

来源: Science Publications

【 摘 要 】

Problem statement: Text summarization takes care of choosing the most significantportions of text and generates coherent summaries that express the main intent of the given document.This study aims to compare the performances of the three text summarization systems developed bythe authors with some of the existing Summarization systems available. These three approaches to textsummarization are based on semantic nets, fuzzy logic and evolutionary programming respectively.All the three represent approaches to achieve connectionism. Approach: First approach performs Partof Speech (POS) tagging, semantic and pragmatic analysis and cohesion. The second system underdiscussion was a new extraction based automated system for text summarization using a decisionmodule that employs fuzzy concepts. Third system under consideration was based on a combination ofevolutionary, fuzzy and connectionist techniques. Results: Semantic net approach performs better thanthe MS Word summarizer as far as the semantics of the original text was concerned. To compare oursummaries with those of the well known MS Word, Intellexer and Copernic summarizers, we useDUC

【 授权许可】

Unknown