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

By Yufeng Zhang, Xueli Yu, Zeyu Cui, Shu Wu, Zhongzheng Wen, Liang Wang. Annual Meeting of the Association for Computational Linguistics, 2020

337 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/23ce8950b9360158c04ab0c1dcf9a73022b60673

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Philip S. Yu
2. Lichao Sun
3. Jiawei Zhang
4. Haopeng Zhang
5. Congying Xia
6. Hao Peng
7. Congyin Xia
8. Jianxin Li

Citations in the corpus

• A Survey on Text Classification: From Shallow to Deep Learning (2020, background): “TextING [163] builds individual graphs for each document and learns text-level word interactions by GNN to effectively produce embeddings for obscure words in the new text.”
• Text Graph Transformer for Document Classification (2020, methodology): “Recently, graph based text classification models received growing attention due to its ability to model global information in corpus (Yao et al., 2019; Peng et al., 2018; Zhang et al., 2020b; Nikolentzos et al., 2019).”
• A Survey on Text Classification: From Traditional to Deep Learning (2020, background): “TextING [162] builds individual graphs for each document and learns text-level word interactions by GNN to effectively produce embeddings for obscure words in the new text.”