BriefGPT.xyz
Nov, 2019
零资源跨语言命名实体识别
Zero-Resource Cross-Lingual Named Entity Recognition
HTML
PDF
M Saiful Bari, Shafiq Joty, Prathyusha Jwalapuram
TL;DR
本文提出一种基于词级对抗训练、参数共享和特征增强的无监督跨语言命名实体识别模型，可在不依靠双语词典或平行数据的情况下，将命名实体知识从一种语言转移到另一种语言。通过对五种不同语言的实验表明，该模型的有效性优于现有模型，并为每个语言对设置了新的 SOTA。
Abstract
Recently,
neural methods
have achieved state-of-the-art (SOTA) results in
named entity recognition
(NER) tasks for many languages without the need for manually crafted features. However, these models still requir
→