POISE: Efficient Cross-Domain Chinese Named Entity Recognization via Transfer Learning

POISE: Efficient Cross-Domain Chinese Named Entity Recognization via Transfer Learning

To improve the performance of deep learning methods in case of a lack of labeled data for entity annotation in entity recognition tasks, this study proposes transfer learning schemes that combine the character to be the word to convert low-resource data symmetry into high-resource data. We combine c...

Full description

Bibliographic Details
Main Authors: Jiabao Sheng, Aishan Wumaier, Zhe Li
Format: Article
Language:English
Published: MDPI AG 2020-10-01
Series:Symmetry
Subjects:
named entity recognition
neural networks
cross-domain
parameter sharing
few resources
Online Access:https://www.mdpi.com/2073-8994/12/10/1673

Internet

https://www.mdpi.com/2073-8994/12/10/1673

Similar Items