Exploiting Global Contextual Information for Document-level Named Entity Recognition

Most existing named entity recognition (NER) approaches are based on sequence labeling models, which focus on capturing the local context dependencies. However, the way of taking one sentence as input prevents the modeling of non-sequential global context, which is useful especially when local conte...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2021-06
Hauptverfasser:	Wang, Zanbo, Wei, Wei, Mao, Xianling, Feng, Shanshan, Zhou, Pan, He, Zhiyong, Jiang, Sheng
Format:	Artikel
Sprache:	eng
Schlagworte:	Context Datasets Graph neural networks Graph theory Modelling Recognition Representations Sentences
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!