The University of Edinburgh's Submission to the WMT22 Code-Mixing Shared Task (MixMT)
This work addresses code-mixed translation challenges for low-resource language pairs, but it is incremental as it builds on existing methods without major breakthroughs.
The University of Edinburgh tackled low-resource code-mixed translation tasks, including generating Hinglish from Hindi/English and translating Hinglish to English, achieving top performance in the WMT22 shared task with baseline systems.
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.