Multi-Level Attention Based Coreference Resolution With Gated Recurrent Unit and Convolutional Neural Networks

Multi-Level Attention Based Coreference Resolution With Gated Recurrent Unit and Convolutional Neural Networks

Aiming at the diversity of the entity mentions in the field of animal husbandry in Tibet, the reference resolution model Att-GRU-CNN based on multi-level attention mechanism is proposed. The model uses GRU network for global semantic feature learning and knowledge memory, and uses CNN network to fur...

Full description

Bibliographic Details
Main Authors: Bianbadroma, Ngodrup, Erping Zhao, Yuhao Wang, Yakun Zhang
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Access
Subjects:
Mention diversity
coreference resolution
attention mechanism
GRU–CNN
data enhancement
Online Access:https://ieeexplore.ieee.org/document/10006801/

Internet

https://ieeexplore.ieee.org/document/10006801/

Similar Items