BriefGPT.xyz
Aug, 2019
低资源形态变化的极限探究
Pushing the Limits of Low-Resource Morphological Inflection
HTML
PDF
Antonios Anastasopoulos, Graham Neubig
TL;DR
提出一种针对低资源语言的自动词形变化生成方案,在神经网络方法、注意力机制、跨语言转移学习等方面做了改进并实现了15%的性能提升。发现了语言类别相似和通用表示是跨语言转移学习成功的关键因素。
Abstract
Recent years have seen exceptional strides in the task of automatic
morphological inflection
generation. However, for a long tail of languages the necessary resources are hard to come by, and state-of-the-art
neural met
→