Few-Shot Named Entity Recognition Based on the Collaborative Graph Attention Network

Few-shot Named Entity Recognition (NER) aims to extract entity information from limited annotated samples, addressing the scarcity of data in specialized domains. However, existing few-shot NER methods relying on data augmentation struggle to adequately augment semantic features, limiting their lear...

Full description

Saved in:
Bibliographic Details
Main Authors: Haoran Niu, Zhaoman Zhong
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10811891/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849713596540387328
author Haoran Niu
Zhaoman Zhong
author_facet Haoran Niu
Zhaoman Zhong
author_sort Haoran Niu
collection DOAJ
description Few-shot Named Entity Recognition (NER) aims to extract entity information from limited annotated samples, addressing the scarcity of data in specialized domains. However, existing few-shot NER methods relying on data augmentation struggle to adequately augment semantic features, limiting their learning and representation capabilities. To overcome this, we introduce a novel few-shot NER encoder based on a Collaborative Graph Attention network (ColGAT). This encoder utilizes a collaborative graph-based data augmentation mechanism to thoroughly extract latent semantic features of entities within sentences, enabling precise entity recognition. Furthermore, to facilitate information interaction between support and query sets, we develop an entity classifier with Match Processing (MP), where adaptive weights allow the support set to flexibly adapt to different query instances, enhancing entity classification performance. Our model achieved an average F1 result of 65.87% across six datasets, surpassing the second-ranked model by 2.19% and achieving state-of-the-art performance, demonstrating significant improvements over previous methods.
format Article
id doaj-art-33c9dde9b6b342ed8c3ff11abfa7d86c
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-33c9dde9b6b342ed8c3ff11abfa7d86c2025-08-20T03:13:55ZengIEEEIEEE Access2169-35362025-01-011312872912874010.1109/ACCESS.2024.352097110811891Few-Shot Named Entity Recognition Based on the Collaborative Graph Attention NetworkHaoran Niu0Zhaoman Zhong1https://orcid.org/0000-0003-0004-3193Jiangsu Ocean University, Lianyungang, Jiangsu, ChinaJiangsu Ocean University, Lianyungang, Jiangsu, ChinaFew-shot Named Entity Recognition (NER) aims to extract entity information from limited annotated samples, addressing the scarcity of data in specialized domains. However, existing few-shot NER methods relying on data augmentation struggle to adequately augment semantic features, limiting their learning and representation capabilities. To overcome this, we introduce a novel few-shot NER encoder based on a Collaborative Graph Attention network (ColGAT). This encoder utilizes a collaborative graph-based data augmentation mechanism to thoroughly extract latent semantic features of entities within sentences, enabling precise entity recognition. Furthermore, to facilitate information interaction between support and query sets, we develop an entity classifier with Match Processing (MP), where adaptive weights allow the support set to flexibly adapt to different query instances, enhancing entity classification performance. Our model achieved an average F1 result of 65.87% across six datasets, surpassing the second-ranked model by 2.19% and achieving state-of-the-art performance, demonstrating significant improvements over previous methods.https://ieeexplore.ieee.org/document/10811891/Few-shot named entity recognitioncollaborative graph attention networkmatch processingdata augmentation
spellingShingle Haoran Niu
Zhaoman Zhong
Few-Shot Named Entity Recognition Based on the Collaborative Graph Attention Network
IEEE Access
Few-shot named entity recognition
collaborative graph attention network
match processing
data augmentation
title Few-Shot Named Entity Recognition Based on the Collaborative Graph Attention Network
title_full Few-Shot Named Entity Recognition Based on the Collaborative Graph Attention Network
title_fullStr Few-Shot Named Entity Recognition Based on the Collaborative Graph Attention Network
title_full_unstemmed Few-Shot Named Entity Recognition Based on the Collaborative Graph Attention Network
title_short Few-Shot Named Entity Recognition Based on the Collaborative Graph Attention Network
title_sort few shot named entity recognition based on the collaborative graph attention network
topic Few-shot named entity recognition
collaborative graph attention network
match processing
data augmentation
url https://ieeexplore.ieee.org/document/10811891/
work_keys_str_mv AT haoranniu fewshotnamedentityrecognitionbasedonthecollaborativegraphattentionnetwork
AT zhaomanzhong fewshotnamedentityrecognitionbasedonthecollaborativegraphattentionnetwork