The Effect of Alignment Objectives on Code-Switching Translation

TL;DR

This paper introduces a unified machine translation model capable of translating both monolingual and code-switched sentences, leveraging synthetic data and alignment loss to improve performance on code-switching content.

Contribution

It proposes a novel training approach with synthetic data and alignment loss, enabling a single model to handle monolingual and code-switched translation tasks effectively.

Findings

Outperforms bidirectional baselines on code-switched translation

Maintains high quality on monolingual translation

Uses synthetic data and alignment loss for improved performance

Abstract

One of the things that need to change when it comes to machine translation is the models' ability to translate code-switching content, especially with the rise of social media and user-generated content. In this paper, we are proposing a way of training a single machine translation model that is able to translate monolingual sentences from one language to another, along with translating code-switched sentences to either language. This model can be considered a bilingual model in the human sense. For better use of parallel data, we generated synthetic code-switched (CSW) data along with an alignment loss on the encoder to align representations across languages. Using the WMT14 English-French (En-Fr) dataset, the trained model strongly outperforms bidirectional baselines on code-switched translation while maintaining quality for non-code-switched (monolingual) data.