Regularized Graph Convolutional Networks for Short Text Classification

Kshitij Tayal, Nikhil Rao, Saurabh Agarwal, Xiaowei Jia, Karthik Subbian, Vipin Kumar


Abstract
Short text classification is a fundamental problem in natural language processing, social network analysis, and e-commerce. The lack of structure in short text sequences limits the success of popular NLP methods based on deep learning. Simpler methods that rely on bag-of-words representations tend to perform on par with complex deep learning methods. To tackle the limitations of textual features in short text, we propose a Graph-regularized Graph Convolution Network (GR-GCN), which augments graph convolution networks by incorporating label dependencies in the output space. Our model achieves state-of-the-art results on both proprietary and external datasets, outperforming several baseline methods by up to 6% . Furthermore, we show that compared to baseline methods, GR-GCN is more robust to noise in textual features.
Anthology ID:
2020.coling-industry.22
Volume:
Proceedings of the 28th International Conference on Computational Linguistics: Industry Track
Month:
December
Year:
2020
Address:
Online
Editors:
Ann Clifton, Courtney Napoles
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
236–242
Language:
URL:
https://aclanthology.org/2020.coling-industry.22
DOI:
10.18653/v1/2020.coling-industry.22
Bibkey:
Cite (ACL):
Kshitij Tayal, Nikhil Rao, Saurabh Agarwal, Xiaowei Jia, Karthik Subbian, and Vipin Kumar. 2020. Regularized Graph Convolutional Networks for Short Text Classification. In Proceedings of the 28th International Conference on Computational Linguistics: Industry Track, pages 236–242, Online. International Committee on Computational Linguistics.
Cite (Informal):
Regularized Graph Convolutional Networks for Short Text Classification (Tayal et al., COLING 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.coling-industry.22.pdf