A Visual Distance for WordNet
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.
Cite
@article{arxiv.1804.09558,
title = {A Visual Distance for WordNet},
author = {Raquel Pérez-Arnal and Armand Vilalta and Dario Garcia-Gasulla and Ulises Cortés and Eduard Ayguadé and Jesus Labarta},
journal= {arXiv preprint arXiv:1804.09558},
year = {2018}
}