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

2020/04/22 by Yufeng Zhang, Zhang, Yufeng, Xueli Yu +9 · 31 citations
Computer Science · Mathematics · #Advanced Graph Neural Networks #Advanced Text Analysis Techniques #Artificial intelligence #Artificial neural network #Benchmark (surveying) #Computation and Language (cs.CL) #Computer science #Document classification #Embedding #FOS: Computer and information sciences #Graph #Mathematics #Natural language processing #Task (project management) #Theoretical computer science #Topic Modeling #Word (group theory) #Word embedding #cs.CL

paper · pdf · doi:10.48550/arxiv.2004.13826

published in arXiv (Cornell University) (Cornell University) · To appear at ACL 2020

openalex publication_date 2020/04/22 · arxiv created 2020/05/12 · arxiv updated 2020/05/13 · openalex created_date 2020/05/13 · openalex updated_date 2026/07/28

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. 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 structures, 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.

Citations

• Glove: Global Vectors for Word Representation

Cited by

• A Novel Graph-Sequence Learning Model for Inductive Text Classification
• GCoDE: Efficient Device-Edge Co-Inference for GNNs via Architecture-Mapping Co-Search
• Three Stage Narrative Analysis; Plot-Sentiment Breakdown, Structure Learning and Concept Detection
• ACE-GNN: Adaptive GNN Co-Inference with System-Aware Scheduling in Dynamic Edge Environments
• Rethinking Graph-Based Document Classification: Learning Data-Driven Structures Beyond Heuristic Approaches
• Enhancing Keyphrase Extraction from Academic Articles Using Section Structure Information
• Benchmarking Graph Neural Networks for Document Layout Analysis in Public Affairs
• RAGAT-Mind: A Multi-Granular Modeling Approach for Rumor Detection Based on MindSpore

Related

• InducT-GCN: Inductive Graph Convolutional Networks for Text Classification
• Graph Neural Networks on Discriminative Graphs of Words
• Graph Convolutional Networks for Text Classification
• Sparse Structure Learning via Graph Neural Networks for Inductive Document Classification
• A text classification method based on LSTM and graph attention network