Computer Science & Electrical

Computer Science & Electrical

Archive
Join as an Editor/Reviewer

Assessing Sentence Similarity using Lexical and semantic Analysis for Text Summarization using Neural Network.

Volume: 4  ,  Issue: 1 , May    Published Date: 19 May 2018
Publisher Name: IJRP
Views: 1099  ,  Download: 475

Authors

# Author Name
1 Abujar Onkon
2 Md. Shahidul Islam
3 Abu Abed Md. Shohaeb

Abstract

This paper has presented sentence similarity measure using lexical and semantic similarity. Degree of similarity was mentioned and implemented in the proposed method. There are few resources available for Bengali language. More development on Bengali language is just more than essential. Bengali WordNet is not stable as like other WordNet available for English language. The key challenges of Natural language Processing is to identify the meaning of any text. Text Summarization is one of the most challenging applications in the field of Natural Language Processing. An expert Text Summarizer need proper analysis of given input text. To identify the degree of relationship among input sentences will help to reduce the inclusion of unimportant sentences in summarized text. This is the objective of this research, to identify similar sentences. Result of summarized text always may not identify by optimal functions, rather a better summarized result could be found by measuring sentence similarities. The current sentence similarity measuring methods only find out the similarity between words and sentences. These methods states only syntactic information of every sentence. There are two major problems to identify similarities between sentences; such problems were never addressed by previous proposed strategies: provide the ultimate meaning of the sentence and added the word order, approximately. In this paper, the main objective was tried to measure sentence similarities, which will help to summarize any Language text, though specially considered for English and Bengali language. The experiment exhibited a proposed method of measuring English and Bengali sentence similarity. Results will states the outstanding performances of our proposed algorithms. Text summarization follows two different methods: Extractive and Abstractive method. Sentence similarity can play a vital role in both, Abstractive and Extractive text summarization approach. Through a proper measurement of sentence similarity, centroid sentences could be extracted and considered as a main and/or leading sentence.

Keywords

  • Sentence Similarity
  • Text Summarization
  • Benglai Summarization
  • Sentence clustering
  • Deep Learning