Text Level Graph Neural Network for Text Classification
Lianzhe Huang, Dehong Ma, Sujian Li, Xiaodong Zhang, Houfeng Wang
Abstract
Recently, researches have explored the graph neural network (GNN) techniques on text classification, since GNN does well in handling complex structures and preserving global information. However, previous methods based on GNN are mainly faced with the practical problems of fixed corpus level graph structure which don’t support online testing and high memory consumption. To tackle the problems, we propose a new GNN based model that builds graphs for each input text with global parameters sharing instead of a single graph for the whole corpus. This method removes the burden of dependence between an individual text and entire corpus which support online testing, but still preserve global information. Besides, we build graphs by much smaller windows in the text, which not only extract more local features but also significantly reduce the edge numbers as well as memory consumption. Experiments show that our model outperforms existing models on several text classification datasets even with consuming less memory.- Anthology ID:
- D19-1345
- Volume:
- Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
- Month:
- November
- Year:
- 2019
- Address:
- Hong Kong, China
- Editors:
- Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
- Venues:
- EMNLP | IJCNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3444–3450
- Language:
- URL:
- https://aclanthology.org/D19-1345
- DOI:
- 10.18653/v1/D19-1345
- Cite (ACL):
- Lianzhe Huang, Dehong Ma, Sujian Li, Xiaodong Zhang, and Houfeng Wang. 2019. Text Level Graph Neural Network for Text Classification. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3444–3450, Hong Kong, China. Association for Computational Linguistics.
- Cite (Informal):
- Text Level Graph Neural Network for Text Classification (Huang et al., EMNLP-IJCNLP 2019)
- PDF:
- https://preview.aclanthology.org/fix-dup-bibkey/D19-1345.pdf
- Code
- mojave-pku/TextLevelGCN + additional community code
- Data
- Ohsumed