Analysis of Word Embeddings Using Fuzzy Clustering

TL;DR

This paper investigates the application of fuzzy clustering algorithms to word embeddings, revealing their sensitivity to high-dimensional data and demonstrating how parameter tuning enhances their effectiveness in analyzing semantic similarities.

Contribution

It introduces a fuzzy clustering approach to analyze word embeddings, showing how parameter tuning improves clustering performance in high-dimensional spaces.

Findings

Fuzzy clustering algorithms are sensitive to high-dimensional data.

Parameter tuning significantly affects clustering performance.

Fuzzy clustering provides insights into word memberships across clusters.

Abstract

In data dominated systems and applications, a concept of representing words in a numerical format has gained a lot of attention. There are a few approaches used to generate such a representation. An interesting issue that should be considered is the ability of such representations - called embeddings - to imitate human-based semantic similarity between words. In this study, we perform a fuzzy-based analysis of vector representations of words, i.e., word embeddings. We use two popular fuzzy clustering algorithms on count-based word embeddings, known as GloVe, of different dimensionality. Words from WordSim-353, called the gold standard, are represented as vectors and clustered. The results indicate that fuzzy clustering algorithms are very sensitive to high-dimensional data, and parameter tuning can dramatically change their performance. We show that by adjusting the value of the fuzzifier parameter, fuzzy clustering can be successfully applied to vectors of high - up to one hundred - dimensions. Additionally, we illustrate that fuzzy clustering allows to provide interesting results regarding membership of words to different clusters.