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.
BibTeX
@inproceedings{tayal-etal-2020-regularized,
title = "Regularized Graph Convolutional Networks for Short Text Classification",
author = "Tayal, Kshitij and
Rao, Nikhil and
Agarwal, Saurabh and
Jia, Xiaowei and
Subbian, Karthik and
Kumar, Vipin",
editor = "Clifton, Ann and
Napoles, Courtney",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics: Industry Track",
month = dec,
year = "2020",
address = "Online",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-industry.22/",
doi = "10.18653/v1/2020.coling-industry.22",
pages = "236--242"
}