Text Categorization as a Graph Classification Problem

By François Rousseau, Emmanouil Kiagias, Michalis Vazirgiannis. 2015

127 citations recorded by the source corpus.

In this paper, we consider the task of text categorization as a graph classification problem. By representing textual documents as graph-of-words instead of historical n-gram bag-of-words, we extract more discriminative features that correspond to long-distance n-grams through frequent subgraph mining. Moreover, by capitalizing on the concept of k-core, we reduce the graph representation to its densest part – its main core – speeding up the feature extraction step for little to no cost in prediction performances. Experiments on four standard text classification datasets show statistically significant higher accuracy and macro-averaged F1-score compared to baseline approaches.

Subfields: Artificial Intelligence, Natural Language Processing, Graph Learning

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. Yangqiu Song
2. Chuan Shi
3. Liang Wang
4. Qiang Yang
5. Linmei Hu
6. Hao Peng
7. Lihong Wang
8. Yaopeng Liu

In Natural Language Processing

1. Liang Wang
2. Chuan Shi
3. Qiang Yang
4. Linmei Hu
5. Yangqiu Song
6. Hao Peng
7. Lihong Wang
8. Yaopeng Liu

In Graph Learning

1. Liang Wang
2. Chuan Shi
3. Qiang Yang
4. Yangqiu Song
5. Hao Peng
6. Lihong Wang
7. Xiaoli Li
8. Shu Wu

Citations in the corpus

• Large-Scale Hierarchical Text Classification with Recursively Regularized Deep Graph-CNN (2018, methodology): “Then given a constructed graph, any sub-graphs can be regarded as long distance n-grams [34].”
• Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networks (2020, methodology): “The text is preprocessed in a standard way, including tokenisation and stopword removal (Blanco and Lioma, 2012; Rousseau et al., 2015).”
• Heterogeneous Graph Attention Networks for Semi-supervised Short Text Classification (2019, background): “Some recent studies (Rousseau et al., 2015; Wang et al., 2016) model texts as graphs and extract path based features for classi-fication.”