BriefGPT.xyz
Aug, 2018
具有最少资源的神经跨语言命名实体识别
Neural Cross-Lingual Named Entity Recognition with Minimal Resources
HTML
PDF
Jiateng Xie, Zhilin Yang, Graham Neubig, Noah A. Smith, Jaime Carbonell
TL;DR
提出了一种基于双语单词嵌入的翻译方法，以改善跨语言的 named-entity recognition 性能，并使用 self-attention 来提高鲁棒性。在对常见语言的测试中达到了最先进或具有竞争力的 NER 性能。
Abstract
For languages with no annotated resources,
unsupervised transfer
of
natural language processing
models such as named-entity recognition (
ner
→