A Neural Approach for Detecting Morphological Analogies

TL;DR

This paper introduces a deep learning method for detecting morphological analogies, demonstrating competitive performance with symbolic approaches and exploring cross-language transferability.

Contribution

It presents a novel neural approach for morphological analogy detection and evaluates its effectiveness and transferability across languages.

Findings

Neural approach is competitive with symbolic methods.

Model shows promising transferability across languages.

Empirical results validate the effectiveness of the proposed method.

Abstract

Analogical proportions are statements of the form "A is to B as C is to D" that are used for several reasoning and classification tasks in artificial intelligence and natural language processing (NLP). For instance, there are analogy based approaches to semantics as well as to morphology. In fact, symbolic approaches were developed to solve or to detect analogies between character strings, e.g., the axiomatic approach as well as that based on Kolmogorov complexity. In this paper, we propose a deep learning approach to detect morphological analogies, for instance, with reinflexion or conjugation. We present empirical results that show that our framework is competitive with the above-mentioned state of the art symbolic approaches. We also explore empirically its transferability capacity across languages, which highlights interesting similarities between them.