期刊
EXPERT SYSTEMS WITH APPLICATIONS
卷 228, 期 -, 页码 -出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.eswa.2023.120435
关键词
Relation extraction; Natural language processing; Attention mechanism; Pre -trained model; Deep learning
The mainstream method of end-to-end relation extraction, which jointly extracts entities and relations, may cause feature conflict. The introduction of advanced pre-trained models allows the use of separate encoders for entity recognition and relation classification, resulting in a promising pipelined approach for relation extraction. By fusing contextual semantic representation and capturing entities' location and type information, this framework achieves better performance than existing models.
The mainstream method of end-to-end relation extraction is to jointly extract entities and relations by sharing span representation, which, however, may cause feature conflict. The advent of advanced pre-trained models enhances the ability to learn span semantic representation and allows the breaking of the dominance of joint models. We argue the benefits of using separate encoders for entity recognition and relation classification and propose a novel pipelined end-to-end relation extraction framework. By adopting attention mechanisms, the framework has the ability to fuse contextual semantic representation, which is missed in other pipelined models. By introducing explicit entity mentions, the framework is able to capture entities' location information and type information, which are difficult to utilize in joint models. Several elaborate tricks are integrated into the training process of the framework to further improve its performance. Our experiments show that our method increases the state-of-the-art relation F1-score on CoNLL04, ADE and SciERC datasets to 75.6% (+1.2%), 85.0% (+1.2%), 43.9% (+2.3%), respectively, indicating that our pipelined approach is promising in end-to-end relation extraction.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据