Hierarchical graph-based text classification framework with contextual node embedding and BERT-based dynamic fusion

Hierarchical graph-based text classification framework with contextual node embedding and BERT-based dynamic fusion

We propose a novel hierarchical graph-based text classification framework that leverages the power of contextual node embedding and BERT-based dynamic fusion to capture the complex relationships between the nodes in the hierarchical graph and generate a more accurate classification of text. The fram...

Celý popis

Podrobná bibliografie
Hlavní autor: Aytuğ Onan
Médium: Článek
Jazyk:English
Vydáno: Elsevier 2023-07-01
Edice:Journal of King Saud University: Computer and Information Sciences
Témata:
Text classification
Hierarchical graph
Pre-trained language models
Contextual embedding
Attention mechanism
On-line přístup:http://www.sciencedirect.com/science/article/pii/S1319157823001647

Internet

http://www.sciencedirect.com/science/article/pii/S1319157823001647

Podobné jednotky