Simplified Graph Learning for Inductive Short Text Classification
Kaixin Zheng, Yaqing Wang, Quanming Yao, Dejing Dou
Abstract
Short text classification (STC) is hard as short texts lack context information and labeled data is not enough. Graph neural networks obtain the state-of-the-art on STC since they can merge various auxiliary information via the message passing framework. However, existing works conduct transductive learning, which requires retraining to accommodate new samples and takes large memory. In this paper, we present SimpleSTC which handles inductive STC problem but only leverages words. We construct word graph from an external large corpus to compensate for the lack of semantic information, and learn text graph to handle the lack of labeled data. Results show that SimpleSTC obtains state-of-the-art performance with lower memory consumption and faster inference speed.
BibTeX
@inproceedings{zheng-etal-2022-simplified,
title = "Simplified Graph Learning for Inductive Short Text Classification",
author = "Zheng, Kaixin and
Wang, Yaqing and
Yao, Quanming and
Dou, Dejing",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.735/",
doi = "10.18653/v1/2022.emnlp-main.735",
pages = "10717--10724"
}