The University of Edinburgh's Submission to the WMT22 Code-Mixing Shared Task (MixMT)

TL;DR

This paper describes the University of Edinburgh's approach to the WMT22 code-mixed translation shared task, focusing on data curation, backtranslation, and pretraining techniques to improve Hinglish translation and generation.

Contribution

The paper introduces effective data generation and pretraining strategies for low-resource code-mixed translation tasks, achieving top performance in the shared task.

Findings

Baseline systems performed best across subtasks.

Careful data curation improved translation quality.

Backtranslation enhanced low-resource translation performance.

Abstract

The University of Edinburgh participated in the WMT22 shared task on code-mixed translation. This consists of two subtasks: i) generating code-mixed Hindi/English (Hinglish) text generation from parallel Hindi and English sentences and ii) machine translation from Hinglish to English. As both subtasks are considered low-resource, we focused our efforts on careful data generation and curation, especially the use of backtranslation from monolingual resources. For subtask 1 we explored the effects of constrained decoding on English and transliterated subwords in order to produce Hinglish. For subtask 2, we investigated different pretraining techniques, namely comparing simple initialisation from existing machine translation models and aligned augmentation. For both subtasks, we found that our baseline systems worked best. Our systems for both subtasks were one of the overall top-performing submissions.