Relation Extraction Using Supervision from Topic Knowledge of Relation Labels
Abstract
Explicitly exploring the semantics of a relation is significant for high-accuracy relation extraction, which is, however, not fully studied in previous work. In this paper, we mine the topic knowledge of a relation to explicitly represent the semantics of this relation, and model relation extraction as a matching problem. That is, the matching score between a sentence and a candidate relation is predicted for an entity pair. To this end, we propose a deep matching network to precisely model the semantic similarity between a sentence-relation pair. Besides, the topic knowledge also allows us to derive the importance information of samples as well as two knowledge-guided negative sampling strategies in the training process. We conduct extensive experiments to evaluate the proposed framework and observe improvements in AUC of 11.5% and max F1 of 5.4% over the baselines with state-of-the-art performance.
Cite
Text
Jiang et al. "Relation Extraction Using Supervision from Topic Knowledge of Relation Labels." International Joint Conference on Artificial Intelligence, 2019. doi:10.24963/IJCAI.2019/698Markdown
[Jiang et al. "Relation Extraction Using Supervision from Topic Knowledge of Relation Labels." International Joint Conference on Artificial Intelligence, 2019.](https://mlanthology.org/ijcai/2019/jiang2019ijcai-relation/) doi:10.24963/IJCAI.2019/698BibTeX
@inproceedings{jiang2019ijcai-relation,
title = {{Relation Extraction Using Supervision from Topic Knowledge of Relation Labels}},
author = {Jiang, Haiyun and Cui, Li and Xu, Zhe and Yang, Deqing and Chen, Jindong and Li, Chenguang and Liu, Jingping and Liang, Jiaqing and Wang, Chao and Xiao, Yanghua and Wang, Wei},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2019},
pages = {5024-5030},
doi = {10.24963/IJCAI.2019/698},
url = {https://mlanthology.org/ijcai/2019/jiang2019ijcai-relation/}
}