TY - GEN
T1 - Dependency-Type Weighted Graph Convolutional Network on End-to-End Aspect-Based Sentiment Analysis
AU - Mu, Yusong
AU - Shi, Shumin
N1 - Publisher Copyright:
© IFIP International Federation for Information Processing 2024.
PY - 2024
Y1 - 2024
N2 - Previous studies consider little on using dependency-type messages in the E2E-ABSA task. Studies using dependency-type messages just contact the dependency-type message and word embedding vectors, which may not fully fuse the context feature and information from the dependency type. This paper proposes a new model called Dependency-Type Weighted Graph Convolution Network (DTW-GCN) to compose dependency-type messages and word embedding. We use a type-weighted matrix to combine the dependency-type message, and DTW-GCN could fuse the dependency-type message and word embedding vectors. Experiments conducted on three benchmark datasets verify the effectiveness of our model.
AB - Previous studies consider little on using dependency-type messages in the E2E-ABSA task. Studies using dependency-type messages just contact the dependency-type message and word embedding vectors, which may not fully fuse the context feature and information from the dependency type. This paper proposes a new model called Dependency-Type Weighted Graph Convolution Network (DTW-GCN) to compose dependency-type messages and word embedding. We use a type-weighted matrix to combine the dependency-type message, and DTW-GCN could fuse the dependency-type message and word embedding vectors. Experiments conducted on three benchmark datasets verify the effectiveness of our model.
KW - Dependency syntactic knowledge
KW - End-to-End Aspect-Based Sentiment Analysis
KW - Graph Convolutional Network
UR - http://www.scopus.com/inward/record.url?scp=85190857874&partnerID=8YFLogxK
U2 - 10.1007/978-3-031-57919-6_4
DO - 10.1007/978-3-031-57919-6_4
M3 - Conference contribution
AN - SCOPUS:85190857874
SN - 9783031579189
T3 - IFIP Advances in Information and Communication Technology
SP - 46
EP - 57
BT - Intelligent Information Processing XII - 13th IFIP TC 12 International Conference, IIP 2024, Proceedings
A2 - Shi, Zhongzhi
A2 - Torresen, Jim
A2 - Yang, Shengxiang
PB - Springer Science and Business Media Deutschland GmbH
T2 - 13th IFIP TC 12 International Conference on Intelligent Information Processing, IIP 2024
Y2 - 3 May 2024 through 6 May 2024
ER -