Connecting the Dots: What Graph-Based Text Representations Work Best for Text Classification using Graph Neural Networks?

Margarita Bugueño, Gerard de Melo


Abstract
Given the success of Graph Neural Networks (GNNs) for structure-aware machine learning, many studies have explored their use for text classification, but mostly in specific domains with limited data characteristics. Moreover, some strategies prior to GNNs relied on graph mining and classical machine learning, making it difficult to assess their effectiveness in modern settings. This work extensively investigates graph representation methods for text classification, identifying practical implications and open challenges. We compare different graph construction schemes using a variety of GNN architectures and setups across five datasets, encompassing short and long documents as well as unbalanced scenarios in diverse domains. Two Transformer-based large language models are also included to complement the study. The results show that i) although the effectiveness of graphs depends on the textual input features and domain, simple graph constructions perform better the longer the documents are, ii) graph representations are especially beneficial for longer documents, outperforming Transformer-based models, iii) graph methods are particularly efficient for solving the task.
Anthology ID:
2023.findings-emnlp.600
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8943–8960
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.600
DOI:
10.18653/v1/2023.findings-emnlp.600
Bibkey:
Cite (ACL):
Margarita Bugueño and Gerard de Melo. 2023. Connecting the Dots: What Graph-Based Text Representations Work Best for Text Classification using Graph Neural Networks?. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 8943–8960, Singapore. Association for Computational Linguistics.
Cite (Informal):
Connecting the Dots: What Graph-Based Text Representations Work Best for Text Classification using Graph Neural Networks? (Bugueño & de Melo, Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.600.pdf