论文标题
语言令牌：一种令人沮丧的简单方法改善了多语言翻译的零击性能
Language Tokens: A Frustratingly Simple Approach Improves Zero-Shot Performance of Multilingual Translation
论文作者
论文摘要
本文提出了一种简单而有效的方法，以改善两种情况下的直接转换（X-to-Y）翻译：零拍摄和直接数据时。我们将编码器和解码器的输入令牌修改为包括源和目标语言的信号。我们在从头开始训练或使用拟议的设置进行预定的模型时会显示出绩效的增长。在实验中，根据检查点选择标准，我们的方法在内部数据集上显示了近10.0个BLEU点的增益。在WMT评估活动中，从英语性能提高了4.17和2.87 BLEU点，在零射击设置中，分别可以进行直接数据进行培训。而X-to-Y在零射基线上提高了1.29 BLEU，而在多到许多基线上则提高了0.44。在低资源设置中，在X-to-Y域数据上进行填充时，我们会看到1.5〜1.7点的改善。
This paper proposes a simple yet effective method to improve direct (X-to-Y) translation for both cases: zero-shot and when direct data is available. We modify the input tokens at both the encoder and decoder to include signals for the source and target languages. We show a performance gain when training from scratch, or finetuning a pretrained model with the proposed setup. In the experiments, our method shows nearly 10.0 BLEU points gain on in-house datasets depending on the checkpoint selection criteria. In a WMT evaluation campaign, From-English performance improves by 4.17 and 2.87 BLEU points, in the zero-shot setting, and when direct data is available for training, respectively. While X-to-Y improves by 1.29 BLEU over the zero-shot baseline, and 0.44 over the many-to-many baseline. In the low-resource setting, we see a 1.5~1.7 point improvement when finetuning on X-to-Y domain data.
