Summer: WeChat Neural Machine Translation Systems for the WMT22 Biomedical Translation Task

TL;DR

This paper presents WeChat's Summer neural machine translation system for Chinese-English biomedical translation in WMT22, utilizing Transformer variants, data techniques, and ensemble methods to achieve top BLEU scores.

Contribution

The paper introduces a novel Transformer-based system with multiple variants and data strategies that significantly improves biomedical translation quality.

Findings

Summer achieves the highest BLEU score among submissions.

Transformer variants and data techniques enhance translation quality.

Ensemble methods contribute to performance gains.

Abstract

This paper introduces WeChat's participation in WMT 2022 shared biomedical translation task on Chinese to English. Our systems are based on the Transformer, and use several different Transformer structures to improve the quality of translation. In our experiments, we employ data filtering, data generation, several variants of Transformer, fine-tuning and model ensemble. Our Chinese$\to$English system, named Summer, achieves the highest BLEU score among all submissions.