Paraphrase Detection using String Similarity with Synonyms

Lee, Jun Choi and Cheah, Yu-N (2015) Paraphrase Detection using String Similarity with Synonyms. In: Fourth Asian Conference on Information Systems, ACIS 2015, 15-16 October 2015, Holiday Inn Resort Penang.

[img]
Preview
 PDF
Paraphrase Detection using String Similarity with Synonyms (abstract).pdf
Download (123kB) | Preview

Abstract

This paper presents an approach to enhance text similarity using synonyms for paraphrase detection. Paraphrase detection detects sentences or texts with similar meaning. Synonym of words can help in paraphrase detection. However, considering synonyms for all the text in the comparison posted extra computational task in the process. This study introduces a simpler approach in considering synonyms in text similarity. The proposed approach is able to be adopted in any term-based text similarity metrics for paraphrase detection. The proposed approach is evaluated using the Microsoft Research Paraphrase Corpus. The evaluation show better result compares to original similarity metrics and reasonable result compares to other selected paraphrase detection approaches in previous studies

Item Type: Proceeding (Paper)
Uncontrolled Keywords: paraphrases detection; string similarities; synonyms; cosine similarity; overlap coefficient; individual match ratio average, unimas, university, universiti, Borneo, Malaysia, Sarawak, Kuching, Samarahan, ipta, education, research, Universiti Malaysia Sarawak
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Academic Faculties, Institutes and Centres > Faculty of Computer Science and Information Technology
Faculties, Institutes, Centres > Faculty of Computer Science and Information Technology
Academic Faculties, Institutes and Centres > Faculty of Computer Science and Information Technology
Depositing User: Mr. Jun Choi Lee
Date Deposited: 29 Aug 2016 20:09
Last Modified: 29 Aug 2016 20:09
URI: http://ir.unimas.my/id/eprint/13241

Actions (For repository members only: login required)

View Item View Item
UNIMAS Institutional Repository is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.