Tackling Morphological Analogies Using Deep Learning -- Extended Version

TL;DR

This paper introduces a deep learning approach for detecting and solving morphological analogies, outperforming symbolic methods by capturing structural properties of words across multiple languages.

Contribution

It presents a novel embedding-based deep learning model that effectively addresses analogy detection and resolution in morphology, surpassing traditional symbolic approaches.

Findings

Deep learning model outperforms symbolic methods in analogy tasks

Model demonstrates robustness to input perturbations

Effective across multiple languages

Abstract

Analogical proportions are statements of the form "A is to B as C is to D". They constitute an inference tool that provides a logical framework to address learning, transfer, and explainability concerns and that finds useful applications in artificial intelligence and natural language processing. In this paper, we address two problems, namely, analogy detection and resolution in morphology. Multiple symbolic approaches tackle the problem of analogies in morphology and achieve competitive performance. We show that it is possible to use a data-driven strategy to outperform those models. We propose an approach using deep learning to detect and solve morphological analogies. It encodes structural properties of analogical proportions and relies on a specifically designed embedding model capturing morphological characteristics of words. We demonstrate our model's competitive performance on analogy detection and resolution over multiple languages. We provide an empirical study to analyze the impact of balancing training data and evaluate the robustness of our approach to input perturbation.