Text Level Graph Neural Network for Text Classification

By Lianzhe Huang, Dehong Ma, Sujian Li, Xiaodong Zhang, Houfeng Wang. Conference on Empirical Methods in Natural Language Processing, 2019

315 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/231b6807767249c04d73c7c6f6295625d4e52591

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. Erik Cambria
3. Jianfeng Gao
4. Jiwei Li
5. Fei Wu
6. Percy Liang
7. Lichao Sun
8. Shervin Minaee

Citations in the corpus

• Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networks (2020, methodology): “In Huang et al. (2019), the edges of the graph are globally fixed between each pair of words, but the fact is that they may affect each other differently in a different text.”
• A Survey on Text Classification: From Traditional to Deep Learning (2020, background): “The SICK contains almost 10,000 English sentence pairs.”
• Aspect-based sentiment analysis via affective knowledge enhanced graph convolutional networks (2021, unknown): “Recently, graph network-based models have achieve promising performance in many NLP tasks, such as text classification [24, 25], relation extraction [26], Chinese NER [27,28].”
• A Survey on Text Classification: From Shallow to Deep Learning (2020, methodology): “To enable GNN-based models to underpin online testing, Huang et al. [137] build graphs for each text with global parameter sharing, not a corpus-level graph structure, to help preserve global information and reduce the burden.”
• Deep Learning--based Text Classification (2020, background): “Depending on the applications at hand, nodes can represent text units of various types, e.g., words, collocations, entire sentences, etc. Similarly, edges can be used to represent different types of relations between any nodes, e.g., lexical or semantic relations, contextual overlap, etc. Modern Gra”
• Text Graph Transformer for Document Classification (2020, methodology): “In addition, we compare with three state-of-the-art GNN-based models: TextGCN in (Yao et al., 2019) using GCN, Text GNN 3 in (Huang et al., 2019) using text level graphs and TensorGCN in (Liu et al., 2020) using semantic and syntactic contextual information.”
• BertGCN: Transductive Text Classification by Combining GNN and BERT (2021, methodology): “Our work is inspired by the work of using graph neural networks for text classification (Yao et al., 2019; Huang et al., 2019; Zhang and Zhang, 2020).”