Improving distantly supervised named entity recognition by emphasizing uncertain examples

Distantly supervised named entity recognition (DS-NER) aims to acquire knowledge from noisy labels. Recently, label re-weighting and label correction based frameworks have been recognized as promising approaches for DS-NER. These methods mainly handle easy or hard examples, yet neglect the impact of...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Pattern analysis and applications : PAA 2025-03, Vol.28 (1), Article 13
Hauptverfasser:	Nie, Binling, Shao, Yiming, Wang, Yigang
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science Labels Pattern Recognition Recognition Theoretical Advances Uncertainty
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!