多语言k近邻机器翻译
Multilingual k-Nearest-Neighbor Machine Translation
AI总结：
本文提出将多种语言表示组合到单一数据存储中，解决k近邻机器翻译在低资源语言上的局限，不仅提升了低资源翻译质量，还通过利用语言相似性缩小数据存储规模并大幅提高速度。
摘要：
k近邻机器翻译通过创建缓存示例的数据存储，在机器翻译质量上展现出显著提升。然而，这些提升仅限于具有大型数据存储的高资源语言对，对低资源语言仍是一项挑战。在本文中，我们通过将多种语言的表示组合到单一数据存储中来解决这一问题。我们的结果一致表明，不仅在低资源翻译质量上有大幅提升（高达+3.6 BLEU），在高资源翻译质量上也有所提高（高达+0.5 BLEU）。实验表明，利用语言相似性创建数据存储，可以构建大小仅为四分之一的多语言数据存储，实现5.3倍的速度提升。
英文摘要：
k-nearest-neighbor machine translation has demonstrated remarkable improvements in machine translation quality by creating a datastore of cached examples. However, these improvements have been limited to high-resource language pairs, with large datastores, and remain a challenge for low-resource languages. In this paper, we address this issue by combining representations from multiple languages into a single datastore. Our results consistently demonstrate substantial improvements not only in low-resource translation quality (up to +3.6 BLEU), but also for high-resource translation quality (up to +0.5 BLEU). Our experiments show that it is possible to create multilingual datastores that are a quarter of the size, achieving a 5.3x speed improvement, by using linguistic similarities for datastore creation.
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。
