A Visual Distance for WordNet

TL;DR

This paper introduces a novel visual-based distance measure for WordNet synsets, leveraging deep neural network features to enhance semantic similarity assessments beyond traditional lexical methods.

Contribution

It proposes a new visual feature-based distance for WordNet synsets using deep learning, complementing existing lexical distance measures.

Findings

Visual distance improves semantic similarity evaluation.

Method outperforms traditional lexical distances in experiments.

Provides a new perspective for concept comparison in NLP.

Abstract

Measuring the distance between concepts is an important field of study of Natural Language Processing, as it can be used to improve tasks related to the interpretation of those same concepts. WordNet, which includes a wide variety of concepts associated with words (i.e., synsets), is often used as a source for computing those distances. In this paper, we explore a distance for WordNet synsets based on visual features, instead of lexical ones. For this purpose, we extract the graphic features generated within a deep convolutional neural networks trained with ImageNet and use those features to generate a representative of each synset. Based on those representatives, we define a distance measure of synsets, which complements the traditional lexical distances. Finally, we propose some experiments to evaluate its performance and compare it with the current state-of-the-art.