Cargando…

Bidirectional matching and aggregation network for few-shot relation extraction

Few-shot relation extraction is used to solve the problem of long tail distribution of data by matching between query instances and support instances. Existing methods focus only on the single direction process of matching, ignoring the symmetry of the data in the process. To address this issue, we...

Descripción completa

Detalles Bibliográficos
Autores principales: Wei, Zhongcheng, Guo, Wenjie, Zhang, Yunping, Zhang, Jieying, Zhao, Jijun
Formato: Online Artículo Texto
Lenguaje:English
Publicado: PeerJ Inc. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10280494/
https://www.ncbi.nlm.nih.gov/pubmed/37346532
http://dx.doi.org/10.7717/peerj-cs.1272
_version_ 1785060806526763008
author Wei, Zhongcheng
Guo, Wenjie
Zhang, Yunping
Zhang, Jieying
Zhao, Jijun
author_facet Wei, Zhongcheng
Guo, Wenjie
Zhang, Yunping
Zhang, Jieying
Zhao, Jijun
author_sort Wei, Zhongcheng
collection PubMed
description Few-shot relation extraction is used to solve the problem of long tail distribution of data by matching between query instances and support instances. Existing methods focus only on the single direction process of matching, ignoring the symmetry of the data in the process. To address this issue, we propose the bidirectional matching and aggregation network (BMAN), which is particularly powerful when the training data is symmetrical. This model not only tries to extract relations for query instances, but also seeks relational prototypes about the query instances to validate the feature representation of the support set. Moreover, to avoid overfitting in bidirectional matching, the data enhancement method was designed to scale up the number of instances while maintaining the scope of the instance relation class. Extensive experiments on FewRel and FewRel2.0 public datasets are conducted and evaluate the effectiveness of BMAN.
format Online
Article
Text
id pubmed-10280494
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher PeerJ Inc.
record_format MEDLINE/PubMed
spelling pubmed-102804942023-06-21 Bidirectional matching and aggregation network for few-shot relation extraction Wei, Zhongcheng Guo, Wenjie Zhang, Yunping Zhang, Jieying Zhao, Jijun PeerJ Comput Sci Artificial Intelligence Few-shot relation extraction is used to solve the problem of long tail distribution of data by matching between query instances and support instances. Existing methods focus only on the single direction process of matching, ignoring the symmetry of the data in the process. To address this issue, we propose the bidirectional matching and aggregation network (BMAN), which is particularly powerful when the training data is symmetrical. This model not only tries to extract relations for query instances, but also seeks relational prototypes about the query instances to validate the feature representation of the support set. Moreover, to avoid overfitting in bidirectional matching, the data enhancement method was designed to scale up the number of instances while maintaining the scope of the instance relation class. Extensive experiments on FewRel and FewRel2.0 public datasets are conducted and evaluate the effectiveness of BMAN. PeerJ Inc. 2023-03-06 /pmc/articles/PMC10280494/ /pubmed/37346532 http://dx.doi.org/10.7717/peerj-cs.1272 Text en © 2023 Wei et al. https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ Computer Science) and either DOI or URL of the article must be cited.
spellingShingle Artificial Intelligence
Wei, Zhongcheng
Guo, Wenjie
Zhang, Yunping
Zhang, Jieying
Zhao, Jijun
Bidirectional matching and aggregation network for few-shot relation extraction
title Bidirectional matching and aggregation network for few-shot relation extraction
title_full Bidirectional matching and aggregation network for few-shot relation extraction
title_fullStr Bidirectional matching and aggregation network for few-shot relation extraction
title_full_unstemmed Bidirectional matching and aggregation network for few-shot relation extraction
title_short Bidirectional matching and aggregation network for few-shot relation extraction
title_sort bidirectional matching and aggregation network for few-shot relation extraction
topic Artificial Intelligence
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10280494/
https://www.ncbi.nlm.nih.gov/pubmed/37346532
http://dx.doi.org/10.7717/peerj-cs.1272
work_keys_str_mv AT weizhongcheng bidirectionalmatchingandaggregationnetworkforfewshotrelationextraction
AT guowenjie bidirectionalmatchingandaggregationnetworkforfewshotrelationextraction
AT zhangyunping bidirectionalmatchingandaggregationnetworkforfewshotrelationextraction
AT zhangjieying bidirectionalmatchingandaggregationnetworkforfewshotrelationextraction
AT zhaojijun bidirectionalmatchingandaggregationnetworkforfewshotrelationextraction