Polysemy Detection in Distributed Representation of Word Sense

TL;DR

This paper introduces a statistical test to identify polysemic words in distributed word representations by analyzing fluctuations in neighboring word senses and their impact on vector positions.

Contribution

It presents a novel statistical method for detecting polysemy in word embeddings, linking sense fluctuations to vector position changes.

Findings

The proposed test effectively identifies polysemic words.

Sense fluctuations influence the position of word vectors.

The method provides insights into how polysemy affects distributed representations.

Abstract

In this paper, we propose a statistical test to determine whether a given word is used as a polysemic word or not. The statistic of the word in this test roughly corresponds to the fluctuation in the senses of the neighboring words a nd the word itself. Even though the sense of a word corresponds to a single vector, we discuss how polysemy of the words affects the position of vectors. Finally, we also explain the method to detect this effect.