Linguistic Dependency Guided Graph Convolutional Networks for Named Entity Recognition

The GCN model used for named entity recognition (NER) tasks reflects promising results by capturing the long-distance syntactic dependency between words in sentences. However, existing models focus on the syntactic relations, we study the usefulness of linguistic, including semantic and syntactic de...

Full description

Saved in:
Bibliographic Details
Published inAdvanced Data Mining and Applications Vol. 13088; pp. 237 - 248
Main Authors Sun, Ximin, Zhou, Jing, Wang, Shuai, Li, Xiaoming, Zheng, Bin, Liu, Dan
Format Book Chapter
LanguageEnglish
Published Switzerland Springer International Publishing AG 2022
Springer International Publishing
SeriesLecture Notes in Computer Science
Subjects
Graph neural network
Linguistic dependency
Named entity recognition
Online AccessGet full text
ISBN9783030954079
3030954072
ISSN0302-9743
1611-3349
DOI10.1007/978-3-030-95408-6_18

Cover

More Information
Summary:The GCN model used for named entity recognition (NER) tasks reflects promising results by capturing the long-distance syntactic dependency between words in sentences. However, existing models focus on the syntactic relations, we study the usefulness of linguistic, including semantic and syntactic dependency types information for NER. Through experiments on the OntoNotes 5.0 data set and ConLL2003 data set, we have demonstrated the significant improvement of our new SDP-GCN NER model.
ISBN:9783030954079
3030954072
ISSN:0302-9743
1611-3349
DOI:10.1007/978-3-030-95408-6_18