Fortification of Neural Morphological Segmentation Models for Polysynthetic Minimal-Resource Languages

TL;DR

This paper enhances neural morphological segmentation for polysynthetic languages with novel multi-task training, data augmentation, and cross-lingual transfer, achieving improved performance in minimal-resource settings.

Contribution

It introduces new multi-task training approaches, data augmentation methods, and demonstrates effective cross-lingual transfer for low-resource polysynthetic languages.

Findings

Neural seq2seq models perform well on Mexican polysynthetic languages with limited data.

Proposed methods improve segmentation accuracy across all tested languages.

A single multilingual model can replace multiple monolingual models, reducing parameters by 75%.

Abstract

Morphological segmentation for polysynthetic languages is challenging, because a word may consist of many individual morphemes and training data can be extremely scarce. Since neural sequence-to-sequence (seq2seq) models define the state of the art for morphological segmentation in high-resource settings and for (mostly) European languages, we first show that they also obtain competitive performance for Mexican polysynthetic languages in minimal-resource settings. We then propose two novel multi-task training approaches -one with, one without need for external unlabeled resources-, and two corresponding data augmentation methods, improving over the neural baseline for all languages. Finally, we explore cross-lingual transfer as a third way to fortify our neural model and show that we can train one single multi-lingual model for related languages while maintaining comparable or even improved performance, thus reducing the amount of parameters by close to 75%. We provide our morphological segmentation datasets for Mexicanero, Nahuatl, Wixarika and Yorem Nokki for future research.