MNet-Sim: A Multi-layered Semantic Similarity Network to Evaluate Sentence Similarity

TL;DR

This paper introduces MNet-Sim, a multi-layered semantic similarity network that combines various similarity measures to improve sentence similarity evaluation across NLP tasks.

Contribution

The paper proposes a novel multi-layered network model utilizing multiple similarity measures and network science principles for more accurate sentence similarity assessment.

Findings

Outperforms existing state-of-the-art models in sentence similarity tasks.

Demonstrates improved accuracy across multiple NLP applications.

Validates effectiveness through extensive testing and comparison.

Abstract

Similarity is a comparative-subjective measure that varies with the domain within which it is considered. In several NLP applications such as document classification, pattern recognition, chatbot question-answering, sentiment analysis, etc., identifying an accurate similarity score for sentence pairs has become a crucial area of research. In the existing models that assess similarity, the limitation of effectively computing this similarity based on contextual comparisons, the localization due to the centering theory, and the lack of non-semantic textual comparisons have proven to be drawbacks. Hence, this paper presents a multi-layered semantic similarity network model built upon multiple similarity measures that render an overall sentence similarity score based on the principles of Network Science, neighboring weighted relational edges, and a proposed extended node similarity computation formula. The proposed multi-layered network model was evaluated and tested against established state-of-the-art models and is shown to have demonstrated better performance scores in assessing sentence similarity.