BriefGPT.xyz
Oct, 2019
为什么使用Attention?分析与修复BiLSTM在建模NER的跨上下文方面的缺陷
Why Attention? Analyzing and Remedying BiLSTM Deficiency in Modeling Cross-Context for NER
HTML
PDF
Peng-Hsuan Li, Tsu-Jui Fu, Wei-Yun Ma
TL;DR
本论文针对BiLSTM模型的局限性,提出两种结构--自注意力和Cross-BiLSTM,用于命名实体识别并在OntoNotes 5.0和WNUT 2017语料集上实现明显且一致的性能提升。
Abstract
State-of-the-art approaches of NER have used sequence-labeling
bilstm
as a core module. This paper formally shows the limitation of
bilstm
in modeling cross-context patterns. Two types of simple
→