Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networks

Yufeng Zhang, Xueli Yu, Zeyu Cui, Shu Wu, Zhongzhen Wen, Liang Wang


Abstract
Text classification is fundamental in natural language processing (NLP) and Graph Neural Networks (GNN) are recently applied in this task. However, the existing graph-based works can neither capture the contextual word relationships within each document nor fulfil the inductive learning of new words. Therefore in this work, to overcome such problems, we propose TextING for inductive text classification via GNN. We first build individual graphs for each document and then use GNN to learn the fine-grained word representations based on their local structure, which can also effectively produce embeddings for unseen words in the new document. Finally, the word nodes are aggregated as the document embedding. Extensive experiments on four benchmark datasets show that our method outperforms state-of-the-art text classification methods.
Anthology ID:
2020.acl-main.31
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
334–339
Language:
URL:
https://aclanthology.org/2020.acl-main.31
DOI:
10.18653/v1/2020.acl-main.31
Bibkey:
Cite (ACL):
Yufeng Zhang, Xueli Yu, Zeyu Cui, Shu Wu, Zhongzhen Wen, and Liang Wang. 2020. Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networks. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 334–339, Online. Association for Computational Linguistics.
Cite (Informal):
Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networks (Zhang et al., ACL 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/2020.acl-main.31.pdf
Video:
 http://slideslive.com/38929373
Code
 CRIPAC-DIG/TextING +  additional community code