Journal
TSINGHUA SCIENCE AND TECHNOLOGY
Volume 27, Issue 3, Pages 610-618Publisher
TSINGHUA UNIV PRESS
DOI: 10.26599/TST.2020.9010059
Keywords
relation extraction; piecewise convolution neural network; adversarial training; generative adversarial network
Categories
Funding
- National Natural Science Foundation of China [U1936104, 2020JCJQ-ZD-012]
Ask authors/readers for more resources
This study proposes a model based on a piecewise convolution neural network with adversarial training to address the issue of data noise in relation extraction. Experiment results show that the model can obtain more accurate training data and outperforms several competitive baseline models.
Most supervised methods for relation extraction (RE) involve time-consuming human annotation. Distant supervision for RE is an efficient method to obtain large corpora that contains thousands of instances and various relations. However, the existing approaches rely heavily on knowledge bases (e.g., Freebase), thereby introducing data noise. Various relations and noisy labeling instances make the issue difficult to solve. In this study, we propose a model based on a piecewise convolution neural network with adversarial training. Inspired by generative adversarial networks, we adopt a heuristic algorithm to identify noisy datasets and apply adversarial training to RE. Experiments on the extended dataset of SemEval-2010 Task 8 show that our model can obtain more accurate training data for RE and significantly outperforms several competitive baseline models. Our model has an Fi score of 89.61%.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available