更快的最近邻机器翻译
Faster Nearest Neighbor Machine Translation
摘要:
基于$k$ NN的神经机器翻译($k$ NN-MT)在多种MT任务中取得了最新的成果。$k$ NN-MT的一个显著缺点在于它在从整个查询中识别查询表示的$k$最近邻居方面的效率低下,当查询大小很大时,这是非常耗时的。在这项工作中,我们提出了\textbf{Faster $k$NN-MT}来解决这个问题。Faster $k$ NN-MT的核心思想是使用层次聚类策略来近似查询与数据点之间的距离,该距离被分解为两部分:查询与数据点所属聚类中心之间的距离,以及数据点与聚类中心之间的距离。我们提出了实际的方法来计算这两个部分在一个显着更快的方式。通过对不同MT基准测试的大量实验,我们表明,\textbf{Faster $k$NN-MT}比Fast $k$ NN-MT \citep{meng2021fast}更快,并且仅比其香草对应物稍慢(1.2倍),同时保持模型性能为$k$ NN-MT。更快的$k$ NN-MT支持在现实世界的MT服务上部署$k$ NN-MT模型。
英文摘要:
$k$NN based neural machine translation ($k$NN-MT) has achieved state-of-the-art results in a variety of MT tasks. One significant shortcoming of $k$NN-MT lies in its inefficiency in identifying the $k$ nearest neighbors of the query representation from the entire datastore, which is prohibitively time-intensive when the datastore size is large. In this work, we propose \textbf{Faster $k$NN-MT} to address this issue. The core idea of Faster $k$NN-MT is to use a hierarchical clustering strategy to approximate the distance between the query and a data point in the datastore, which is decomposed into two parts: the distance between the query and the center of the cluster that the data point belongs to, and the distance between the data point and the cluster center. We propose practical ways to compute these two parts in a significantly faster manner. Through extensive experiments on different MT benchmarks, we show that \textbf{Faster $k$NN-MT} is faster than Fast $k$NN-MT \citep{meng2021fast} and only slightly (1.2 times) slower than its vanilla counterpart while preserving model performance as $k$NN-MT. Faster $k$NN-MT enables the deployment of $k$NN-MT models on real-world MT services.
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。