A Dynamic Parameter Enhanced Network for distant supervised relation extraction

作者：

Highlights：

• We utilize the class connection with entity types to boost Distant Supervised Relation Extraction.

• We propose a dynamic parameter enhanced network to improve the prediction accuracy.

• We propose a relation-aware attention over entity types to select the discriminative entity types.

• Extensive experiments show that our method gives new state-of-the-art performance.

摘要

•We utilize the class connection with entity types to boost Distant Supervised Relation Extraction.•We propose a dynamic parameter enhanced network to improve the prediction accuracy.•We propose a relation-aware attention over entity types to select the discriminative entity types.•Extensive experiments show that our method gives new state-of-the-art performance.

论文关键词：Distant supervision,Relation extraction,Dynamic parameter,Style shift,Long-tail relation

论文评审过程：Received 10 December 2019, Revised 23 February 2020, Accepted 10 April 2020, Available online 14 April 2020, Version of Record 24 April 2020.

论文官网地址：https://doi.org/10.1016/j.knosys.2020.105912