On the Transferability of Neural Models of Morphological Analogies

TL;DR

This paper investigates how neural models for morphological analogies transfer across languages, revealing insights into multilingual morphological modeling and its potential applications.

Contribution

It introduces a deep learning framework for morphological analogy detection and provides an empirical study on cross-lingual transferability, highlighting language similarities and differences.

Findings

Models transfer effectively across some languages

Identifies language-specific challenges in transferability

Suggests potential for multilingual morphological models

Abstract

Analogical proportions are statements expressed in the form "A is to B as C is to D" and are used for several reasoning and classification tasks in artificial intelligence and natural language processing (NLP). In this paper, we focus on morphological tasks and we propose a deep learning approach to detect morphological analogies. We present an empirical study to see how our framework transfers across languages, and that highlights interesting similarities and differences between these languages. In view of these results, we also discuss the possibility of building a multilingual morphological model.