Computing Fuzzy Rough Set based Similarities with Fuzzy Inference and Its Application to Sentence Similarity Computations

TL;DR

This paper introduces a novel method that combines fuzzy rough set similarities using fuzzy inference to improve sentence similarity measurement, demonstrating its effectiveness on the SICK2014 dataset.

Contribution

It proposes a new technique to integrate lower and upper fuzzy rough set similarities via fuzzy inference, applied to sentence similarity computation.

Findings

Effective combination of similarity measures improves accuracy

Method outperforms existing approaches on SICK2014 dataset

Fuzzy inference enhances fuzzy rough set applications in NLP

Abstract

Several research initiatives have been proposed for computing similarity between two Fuzzy Sets in analysis through Fuzzy Rough Sets. These techniques yield two measures viz. lower similarity and upper similarity. While in most applications only one entity is useful to further analysis and for drawing conclusions. The aim of this paper is to propose novel technique to combine Fuzzy Rough Set based lower similarity and upper similarity using Fuzzy Inference Engine. Further, the proposed approach is applied to the problem computing sentence similarity and have been evaluated on SICK2014 dataset.