Paradigm Completion for Derivational Morphology

TL;DR

This paper introduces the task of derivational paradigm completion in NLP, applying neural sequence-to-sequence models to generate complex derived words, and demonstrates their effectiveness over non-neural baselines.

Contribution

It formulates derivational paradigm completion as a new task and adapts neural models from inflection to improve derivational morphology processing.

Findings

Neural models outperform non-neural baselines by 16.4%.

Models learn a range of derivation patterns.

Future work needed for parity with inflection systems.

Abstract

The generation of complex derived word forms has been an overlooked problem in NLP; we fill this gap by applying neural sequence-to-sequence models to the task. We overview the theoretical motivation for a paradigmatic treatment of derivational morphology, and introduce the task of derivational paradigm completion as a parallel to inflectional paradigm completion. State-of-the-art neural models, adapted from the inflection task, are able to learn a range of derivation patterns, and outperform a non-neural baseline by 16.4%. However, due to semantic, historical, and lexical considerations involved in derivational morphology, future work will be needed to achieve performance parity with inflection-generating systems.