SIT at MixMT 2022: Fluent Translation Built on Giant Pre-trained Models
This work addresses code-mixed translation for languages like Hindi and English, but it is incremental as it applies existing methods to a specific shared task.
The paper tackled the WMT 2022 code-mixed machine translation task by using large pre-trained models and techniques like back-translation, achieving first place in subtask 2 and top positions in subtask 1 based on metrics such as ROUGE-L and WER.
This paper describes the Stevens Institute of Technology's submission for the WMT 2022 Shared Task: Code-mixed Machine Translation (MixMT). The task consisted of two subtasks, subtask $1$ Hindi/English to Hinglish and subtask $2$ Hinglish to English translation. Our findings lie in the improvements made through the use of large pre-trained multilingual NMT models and in-domain datasets, as well as back-translation and ensemble techniques. The translation output is automatically evaluated against the reference translations using ROUGE-L and WER. Our system achieves the $1^{st}$ position on subtask $2$ according to ROUGE-L, WER, and human evaluation, $1^{st}$ position on subtask $1$ according to WER and human evaluation, and $3^{rd}$ position on subtask $1$ with respect to ROUGE-L metric.