KGNER: Improving Chinese Named Entity Recognition by BERT Infused with the Knowledge Graph

Recently, the lexicon method has been proven to be effective for named entity recognition (NER). However, most existing lexicon-based methods cannot fully utilize common-sense knowledge in the knowledge graph. For example, the word embeddings pretrained by Word2vector or Glove lack better contextual...

Полное описание

Библиографические подробности

Главные авторы:	Weiwei Hu, Liang He, Hanhan Ma, Kai Wang, Jingfeng Xiao
Формат:	Artigo
Язык:	Inglês
Опубликовано:	MDPI AG 2022-07-01
Серии:	Applied Sciences
Предметы:	named-entity recognition knowledge graph conditional random field
Online-ссылка:	https://www.mdpi.com/2076-3417/12/15/7702
Метки:	Добавить метку Нет меток, Требуется 1-ая метка записи!