A Preordered RNN Layer Boosts Neural Machine Translation in Low Resource Settings

TL;DR

This paper introduces a preordered RNN layer that incorporates reordering information into neural machine translation models, significantly improving translation quality in low-resource language settings.

Contribution

It proposes a novel preordered RNN layer that enhances NMT models by integrating reordering info, addressing data scarcity issues.

Findings

Up to 6% BLEU improvement over baseline models

Effective for English-Persian translation

Enhances translation quality in low-resource scenarios

Abstract

Neural Machine Translation (NMT) models are strong enough to convey semantic and syntactic information from the source language to the target language. However, these models are suffering from the need for a large amount of data to learn the parameters. As a result, for languages with scarce data, these models are at risk of underperforming. We propose to augment attention based neural network with reordering information to alleviate the lack of data. This augmentation improves the translation quality for both English to Persian and Persian to English by up to 6% BLEU absolute over the baseline models.