BriefGPT.xyz
Nov, 2020
为低资源神经机器翻译优化Transformer
Optimizing Transformer for Low-Resource Neural Machine Translation
HTML
PDF
Ali Araabi, Christof Monz
TL;DR
本文研究了神经机器翻译中低资源语种的问题，通过在IWSLT14数据集上的实验发现，在优化超参数设置的情况下，Transformer模型在低资源情况下的翻译质量可以提高7.3个BLEU分数。
Abstract
Language pairs with limited amounts of parallel data, also known as
low-resource languages
, remain a challenge for
neural machine translation
. While the
→