Improved relation classification by deep recurrent neural networks with data augmentation
Full Text: C16-1138.pdf
Nowadays, neural networks play an important role in the task of relation classification. By designing different neural architectures, researchers have improved the performance to a large extent in comparison with traditional methods. However, existing neural networks for relation classification are usually of shallow architectures (e.g., one-layer convolutional neural networks or recurrent networks). They may fail to explore the potential representation space in different abstraction levels. In this paper, we propose deep recurrent neural networks (DRNNs) for relation classification to tackle this challenge. Further, we propose a data augmentation method by leveraging the directionality of relations. We evaluated our DRNNs on the SemEval-2010 Task 8, and achieve an F1-score of 86.1%, outperforming previous state-of-the-art recorded results.
Citation
Y. Xu, R. Jia, L. Mou, G. Li, Y. Chen, Y. Lu, Z. Jin. "Improved relation classification by deep recurrent neural networks with data augmentation". Conference on Computational Linguistics (COLING), pp 1461–1470, December 2016.| Keywords: | |
| Category: | In Conference |
| Web Links: | ACL |
BibTeX
@incollection{Xu+al:COLING16,
author = {Yan Xu and Ran Jia and Lili Mou and Ge Li and Yunchuan Chen and
Yangyang Lu and Zhi Jin},
title = {Improved relation classification by deep recurrent neural networks
with data augmentation},
Pages = {1461–1470},
booktitle = {Conference on Computational Linguistics (COLING)},
year = 2016,
}Last Updated: February 03, 2021Submitted by Sabina P
