Graph Ensemble Learning over Multiple Dependency Trees for Aspect-level Sentiment Classification
Xiaochen Hou, Peng Qi, Guangtao Wang, Rex Ying, Jing Huang, Xiaodong He, Bowen Zhou
Abstract
Recent work on aspect-level sentiment classification has demonstrated the efficacy of incorporating syntactic structures such as dependency trees with graph neural networks (GNN), but these approaches are usually vulnerable to parsing errors. To better leverage syntactic information in the face of unavoidable errors, we propose a simple yet effective graph ensemble technique, GraphMerge, to make use of the predictions from different parsers. Instead of assigning one set of model parameters to each dependency tree, we first combine the dependency relations from different parses before applying GNNs over the resulting graph. This allows GNN models to be robust to parse errors at no additional computational cost, and helps avoid overparameterization and overfitting from GNN layer stacking by introducing more connectivity into the ensemble graph. Our experiments on the SemEval 2014 Task 4 and ACL 14 Twitter datasets show that our GraphMerge model not only outperforms models with single dependency tree, but also beats other ensemble models without adding model parameters.
BibTeX
@inproceedings{hou-etal-2021-graph,
title = "Graph Ensemble Learning over Multiple Dependency Trees for Aspect-level Sentiment Classification",
author = "Hou, Xiaochen and
Qi, Peng and
Wang, Guangtao and
Ying, Rex and
Huang, Jing and
He, Xiaodong and
Zhou, Bowen",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.229/",
doi = "10.18653/v1/2021.naacl-main.229",
pages = "2884--2894"
}