Investigating Backtranslation in Neural Machine Translation

TL;DR

This paper investigates the effects of using back-translated monolingual data on neural machine translation performance, analyzing how different amounts influence translation quality in German-to-English translation.

Contribution

It provides a detailed analysis of how back-translated data impacts NMT performance, including effects of data size and combination with authentic data.

Findings

Back-translated data improves NMT performance, especially in resource-scarce scenarios.

The impact varies with the amount of back-translated data used.

Combining back-translated with authentic data yields better results than using either alone.

Abstract

A prerequisite for training corpus-based machine translation (MT) systems -- either Statistical MT (SMT) or Neural MT (NMT) -- is the availability of high-quality parallel data. This is arguably more important today than ever before, as NMT has been shown in many studies to outperform SMT, but mostly when large parallel corpora are available; in cases where data is limited, SMT can still outperform NMT. Recently researchers have shown that back-translating monolingual data can be used to create synthetic parallel corpora, which in turn can be used in combination with authentic parallel data to train a high-quality NMT system. Given that large collections of new parallel text become available only quite rarely, backtranslation has become the norm when building state-of-the-art NMT systems, especially in resource-poor scenarios. However, we assert that there are many unknown factors regarding the actual effects of back-translated data on the translation capabilities of an NMT model. Accordingly, in this work we investigate how using back-translated data as a training corpus -- both as a separate standalone dataset as well as combined with human-generated parallel data -- affects the performance of an NMT model. We use incrementally larger amounts of back-translated data to train a range of NMT systems for German-to-English, and analyse the resulting translation performance.