A Hierarchical Heterogeneous Graph Attention Network for Emotion-Cause Pair Extraction
Recently, graph neural networks (GNN), due to their compelling representation learning ability, have been exploited to deal with emotion-cause pair extraction (ECPE). However, current GNN-based ECPE methods mostly concentrate on modeling the local dependency relation between homogeneous nodes at the...
Main Authors: | Jiaxin Yu, Wenyuan Liu, Yongjun He, Bineng Zhong |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-09-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/11/18/2884 |
Similar Items
-
Utilizing Heterogeneous Graph Neural Network to Extract Emotion-Cause Pairs Effectively
by: PU Jinyao, BU Lingmei, LU Yongmei, YE Ziming, CHEN Li, YU Zhonghua
Published: (2023-01-01) -
LEHAN: Link-Feature Enhanced Heterogeneous Graph Attention Network
by: Jongmin Park, et al.
Published: (2022-01-01) -
Short Text Classification Based on Hierarchical Heterogeneous Graph and LDA Fusion
by: Xinlan Xu, et al.
Published: (2023-06-01) -
SR-HGAT: Symmetric Relations Based Heterogeneous Graph Attention Network
by: Zhenghao Zhang, et al.
Published: (2020-01-01) -
MBHAN: Motif-Based Heterogeneous Graph Attention Network
by: Qian Hu, et al.
Published: (2022-06-01)