BriefGPT.xyz
May, 2017
使用双语词典进行标注低资源语言的模型转移
Model Transfer for Tagging Low-resource Languages using a Bilingual Dictionary
HTML
PDF
Meng Fang, Trevor Cohn
TL;DR
本研究提出了一种新颖的基于跨语言词向量的神经网络模型,通过高覆盖的双语词典训练,利用跨语言模型转移的方法,针对低资源语言的注释预测问题提出了解决方案,并通过多种主动学习启发式方法,提升了该方法的性能。
Abstract
cross-lingual model transfer
is a compelling and popular method for predicting annotations in a
low-resource language
, whereby parallel corpora provide a bridge to a high-resource language and its associated anno
→