Low Resourced Machine Translation via Morpho-syntactic Modeling: The Case of Dialectal Arabic

TL;DR

This paper explores dialect-to-dialect Arabic machine translation, demonstrating that morpho-syntactic modeling and external resources significantly enhance translation quality in low-resource settings.

Contribution

It is the first to evaluate dialect-to-dialect Arabic translation using external resources and morpho-syntactic modeling, advancing low-resource MT research.

Findings

Morpho-syntactic modeling improves translation quality.

External resources enhance low-resource dialect translation.

Performance increases from 6.5 BLEU to 17.5 BLEU with proposed methods.

Abstract

We present the second ever evaluated Arabic dialect-to-dialect machine translation effort, and the first to leverage external resources beyond a small parallel corpus. The subject has not previously received serious attention due to lack of naturally occurring parallel data; yet its importance is evidenced by dialectal Arabic's wide usage and breadth of inter-dialect variation, comparable to that of Romance languages. Our results suggest that modeling morphology and syntax significantly improves dialect-to-dialect translation, though optimizing such data-sparse models requires consideration of the linguistic differences between dialects and the nature of available data and resources. On a single-reference blind test set where untranslated input scores 6.5 BLEU and a model trained only on parallel data reaches 14.6, pivot techniques and morphosyntactic modeling significantly improve performance to 17.5.