面向 VLSP 2022 的 VBD-MT 中越翻译系统
VBD-MT Chinese-Vietnamese Translation Systems for VLSP 2022
AI总结:
本文提出参加 VLSP 2022 的中越双向机器翻译系统,结合 Transformer、mBART、回译采样、集成与后处理,在公共测试集上取得优于强基线的 BLEU 成绩。
摘要:
我们介绍了参加 VLSP 2022 机器翻译共享任务的系统。在今年的共享任务中,我们参加了两个翻译任务,即中译越和越译中。我们基于神经 Transformer 模型构建系统,并采用功能强大的多语言去噪预训练模型 mBART。系统通过一种用于回译的采样方法得到增强,该方法利用了大规模可用单语数据。此外,还应用了包括集成和后处理在内的其他几种方法来提升翻译质量。在公共测试集上,我们的中译越系统达到 38.9 BLEU,越译中系统达到 38.0 BLEU,表现优于多个强基线。
英文摘要:
We present our systems participated in the VLSP 2022 machine translation shared task. In the shared task this year, we participated in both translation tasks, i.e., Chinese-Vietnamese and Vietnamese-Chinese translations. We build our systems based on the neural-based Transformer model with the powerful multilingual denoising pre-trained model mBART. The systems are enhanced by a sampling method for backtranslation, which leverage large scale available monolingual data. Additionally, several other methods are applied to improve the translation quality including ensembling and postprocessing. We achieve 38.9 BLEU on ChineseVietnamese and 38.0 BLEU on VietnameseChinese on the public test sets, which outperform several strong baselines.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。