Learning Subword Embedding to Improve Uyghur Named-Entity Recognition

Learning Subword Embedding to Improve Uyghur Named-Entity Recognition

Uyghur is a morphologically rich and typical agglutinating language, and morphological segmentation affects the performance of Uyghur named-entity recognition (NER). Common Uyghur NER systems use the word sequence as input and rely heavily on feature engineering. However, semantic information cannot...

Full description

Bibliographic Details
Main Authors: Alimu Saimaiti, Lulu Wang, Tuergen Yibulayin
Format: Article
Language:English
Published: MDPI AG 2019-04-01
Series:Information
Subjects:
subword embedding
Uyghur
named-entity recognition
morphological processing
word sequence
natural language processing
deep learning
word-based neural model
Online Access:https://www.mdpi.com/2078-2489/10/4/139

Internet

https://www.mdpi.com/2078-2489/10/4/139

Similar Items