Single-Model Encoder-Decoder with Explicit Morphological Representation for Reinflection

TL;DR

This paper introduces a neural encoder-decoder model with explicit morphological representation for morphological reinflection, achieving state-of-the-art results especially in low-resource language scenarios.

Contribution

It presents a novel modeling approach that reduces training data needs and incorporates an automatic correction method using edit trees.

Findings

Achieves state-of-the-art accuracy in morphological reinflection

Effective for low-resource languages

Introduces an automatic output correction technique

Abstract

Morphological reinflection is the task of generating a target form given a source form, a source tag and a target tag. We propose a new way of modeling this task with neural encoder-decoder models. Our approach reduces the amount of required training data for this architecture and achieves state-of-the-art results, making encoder-decoder models applicable to morphological reinflection even for low-resource languages. We further present a new automatic correction method for the outputs based on edit trees.