摘要
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.
源语言 | 英语 |
---|---|
主期刊名 | Intelligent Information Processing XII - 13th IFIP TC 12 International Conference, IIP 2024, Proceedings |
编辑 | Zhongzhi Shi, Jim Torresen, Shengxiang Yang |
出版商 | Springer Science and Business Media Deutschland GmbH |
页 | 46-57 |
页数 | 12 |
ISBN(印刷版) | 9783031579189 |
DOI | |
出版状态 | 已出版 - 2024 |
活动 | 13th IFIP TC 12 International Conference on Intelligent Information Processing, IIP 2024 - Shenzhen, 中国 期限: 3 5月 2024 → 6 5月 2024 |
出版系列
姓名 | IFIP Advances in Information and Communication Technology |
---|---|
卷 | 704 IFIPAICT |
ISSN(印刷版) | 1868-4238 |
ISSN(电子版) | 1868-422X |
会议
会议 | 13th IFIP TC 12 International Conference on Intelligent Information Processing, IIP 2024 |
---|---|
国家/地区 | 中国 |
市 | Shenzhen |
时期 | 3/05/24 → 6/05/24 |
指纹
探究 'Dependency-Type Weighted Graph Convolutional Network on End-to-End Aspect-Based Sentiment Analysis' 的科研主题。它们共同构成独一无二的指纹。引用此
Mu, Y., & Shi, S. (2024). Dependency-Type Weighted Graph Convolutional Network on End-to-End Aspect-Based Sentiment Analysis. 在 Z. Shi, J. Torresen, & S. Yang (编辑), Intelligent Information Processing XII - 13th IFIP TC 12 International Conference, IIP 2024, Proceedings (页码 46-57). (IFIP Advances in Information and Communication Technology; 卷 704 IFIPAICT). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-57919-6_4