Robust triple extraction with cascade bidirectional capsule network
作者:
Highlights:
• The first model using capsule network in triple extraction.
• Modeling the parts-wholes between entities and relations.
• A robust model for triple extraction with diverse surface forms.
• Can handle overlapping relational triples.
• Good performance in benchmarks and obtain better results in robust settings.
摘要
•The first model using capsule network in triple extraction.•Modeling the parts-wholes between entities and relations.•A robust model for triple extraction with diverse surface forms.•Can handle overlapping relational triples.•Good performance in benchmarks and obtain better results in robust settings.
论文关键词:Triple extraction,Relation extraction,Entity recognition
论文评审过程:Received 19 August 2020, Revised 25 June 2021, Accepted 23 August 2021, Available online 24 September 2021, Version of Record 29 September 2021.
论文官网地址:https://doi.org/10.1016/j.eswa.2021.115806