A Visual Distance for WordNet
This work addresses concept distance measurement in Natural Language Processing, offering a novel visual-based approach that could enhance tasks like concept interpretation, though it appears incremental as it builds on existing methods.
The paper tackles the problem of measuring distances between WordNet synsets by introducing a visual distance based on deep convolutional neural network features from ImageNet, complementing traditional lexical distances, and reports performance comparisons with state-of-the-art methods.
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.