Multi-Attention-Based Capsule Network for Uyghur Personal Pronouns Resolution

Multi-Attention-Based Capsule Network for Uyghur Personal Pronouns Resolution

Anaphora resolution of Uyghur is a challenging task because of complex language structure and limited corpus. We propose a multi-attention based capsule network model for Uyghur personal pronouns resolution, which can obtain the multi-layer and implicit semantic information effectively. Independentl...

Full description

Bibliographic Details
Main Authors: Qimeng Yang, Long Yu, Shengwei Tian, Jinmiao Song
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Capsule network
anaphora resolution
IndRNN
attention mechanism
Online Access:https://ieeexplore.ieee.org/document/9076012/

Internet

https://ieeexplore.ieee.org/document/9076012/

Similar Items