Cross-lingual Inflection as a Data Augmentation Method for Parsing

TL;DR

This paper introduces a morphology-based data augmentation technique using cross-lingual inflection to improve low-resource dependency parsing, showing mixed but sometimes positive results.

Contribution

It presents a novel method of generating augmented treebanks via morphological inflection from related languages for low-resource parsing.

Findings

Method sometimes improves parsing accuracy.

Effectiveness varies depending on language pair.

Provides a new approach for low-resource language NLP.

Abstract

We propose a morphology-based method for low-resource (LR) dependency parsing. We train a morphological inflector for target LR languages, and apply it to related rich-resource (RR) treebanks to create cross-lingual (x-inflected) treebanks that resemble the target LR language. We use such inflected treebanks to train parsers in zero- (training on x-inflected treebanks) and few-shot (training on x-inflected and target language treebanks) setups. The results show that the method sometimes improves the baselines, but not consistently.