Graph Convolutional Networks for Text Classification

Abstract

Text classification is an important and classical problem in natural language processing. There have been a number of studies that applied convolutional neural networks (convolution on regular grid, e.g., sequence) to classification. However, only a limited number of studies have explored the more flexible graph convolutional neural networks (convolution on non-grid, e.g., arbitrary graph) for the task. In this work, we propose to use graph convolutional networks for text classification. We build a single text graph for a corpus based on word co-occurrence and document word relations, then learn a Text Graph Convolutional Network (Text GCN) for the corpus. Our Text GCN is initialized with one-hot representation for word and document, it then jointly learns the embeddings for both words and documents, as supervised by the known class labels for documents. Our experimental results on multiple benchmark datasets demonstrate that a vanilla Text GCN without any external word embeddings or knowledge outperforms state-of-the-art methods for text classification. On the other hand, Text GCN also learns predictive word and document embeddings. In addition, experimental results show that the improvement of Text GCN over state-of-the-art comparison methods become more prominent as we lower the percentage of training data, suggesting the robustness of Text GCN to less training data in text classification.

arXiv commentAccepted by 33rd AAAI Conference on Artificial Intelligence (AAAI 2019)

References in corpus (5)

• Inductive Representation Learning on Large Graphs
• Deep Convolutional Networks on Graph-Structured Data
• Seeing stars: Exploiting class relationships for sentiment categorization with respect to rating scales
• FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
• Sentence-State LSTM for Text Representation

Cited by in corpus (16)

• Graph Star Net for Generalized Multi-Task Learning
• Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs
• Understanding GNN Computational Graph: A Coordinated Computation, IO, and Memory Perspective
• Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks
• Recursive Graphical Neural Networks for Text Classification
• Coherent Comment Generation for Chinese Articles with a Graph-to-Sequence Model
• Multi-Label Graph Convolutional Network Representation Learning
• Interpretable Text Classification Using CNN and Max-pooling
• Graph Sequential Network for Reasoning over Sequences
• Detecting Hostile Posts using Relational Graph Convolutional Network
• Dual-Attention Graph Convolutional Network
• Hybrid Low-order and Higher-order Graph Convolutional Networks
• Semantic Graph Convolutional Network for Implicit Discourse Relation Classification
• geoGAT: Graph Model Based on Attention Mechanism for Geographic Text Classification
• DNA-GCN: Graph convolutional networks for predicting DNA-protein binding
• Relevant Region Prediction for Crowd Counting