Label-Specific Dual Graph Neural Network for Multi-Label Text Classification

Qianwen Ma, Chunyuan Yuan, Wei Zhou, Songlin Hu


Abstract
Multi-label text classification is one of the fundamental tasks in natural language processing. Previous studies have difficulties to distinguish similar labels well because they learn the same document representations for different labels, that is they do not explicitly extract label-specific semantic components from documents. Moreover, they do not fully explore the high-order interactions among these semantic components, which is very helpful to predict tail labels. In this paper, we propose a novel label-specific dual graph neural network (LDGN), which incorporates category information to learn label-specific components from documents, and employs dual Graph Convolution Network (GCN) to model complete and adaptive interactions among these components based on the statistical label co-occurrence and dynamic reconstruction graph in a joint way. Experimental results on three benchmark datasets demonstrate that LDGN significantly outperforms the state-of-the-art models, and also achieves better performance with respect to tail labels.
Anthology ID:
2021.acl-long.298
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3855–3864
Language:
URL:
https://aclanthology.org/2021.acl-long.298
DOI:
10.18653/v1/2021.acl-long.298
Bibkey:
Cite (ACL):
Qianwen Ma, Chunyuan Yuan, Wei Zhou, and Songlin Hu. 2021. Label-Specific Dual Graph Neural Network for Multi-Label Text Classification. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 3855–3864, Online. Association for Computational Linguistics.
Cite (Informal):
Label-Specific Dual Graph Neural Network for Multi-Label Text Classification (Ma et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.298.pdf
Video:
 https://aclanthology.org/2021.acl-long.298.mp4
Data
RCV1