Nested relation extraction via self-contrastive learning guided by structure and semantic similarity

The conventional Relation Extraction (RE) task involves identifying whether relations exist between two entities in a given sentence and determining their relation types. However, the complexity of practical application scenarios and the flexibility of natural language demand the ability to extract...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Neural networks 2023-05, Vol.162, p.393-411
Hauptverfasser:	Mai, Chengcheng, Luo, Kaiwen, Wang, Yuxiang, Peng, Ziyan, Chen, Yu, Yuan, Chunfeng, Huang, Yihua
Format:	Artikel
Sprache:	eng
Schlagworte:	Iterative neural networks Language Learning Natural Language Processing Nested relation extraction Neural Networks, Computer Self-contrastive learning Semantic similarity Semantics Structure similarity
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!