BriefGPT.xyz
Apr, 2024
跨语言、字符级别的低资源命名实体识别的神经条件随机场
Low-Resource Named Entity Recognition with Cross-Lingual, Character-Level Neural Conditional Random Fields
HTML
PDF
Ryan Cotterell, Kevin Duh
TL;DR
通过字符级神经CRF模型进行跨多个语言的命名实体识别的迁移学习，使得在资源丰富和资源匮乏的语言中都能提高F1分数，并在基线上提升9.8个点。
Abstract
low-resource
named entity recognition
is still an open problem in NLP. Most state-of-the-art systems require tens of thousands of annotated sentences in order to obtain high performance. However, for most of the
→