A Concise Relation Extraction Method Based on the Fusion of Sequential and Structural Features Using ERNIE
Relation extraction, a fundamental task in natural language processing, aims to extract entity triples from unstructured data. These triples can then be used to build a knowledge graph. Recently, pre-training models that have learned prior semantic and syntactic knowledge, such as BERT and ERNIE, ha...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-03-01
|
Series: | Mathematics |
Subjects: | |
Online Access: | https://www.mdpi.com/2227-7390/11/6/1439 |
_version_ | 1797610319458074624 |
---|---|
author | Yu Wang Yuan Wang Zhenwan Peng Feifan Zhang Fei Yang |
author_facet | Yu Wang Yuan Wang Zhenwan Peng Feifan Zhang Fei Yang |
author_sort | Yu Wang |
collection | DOAJ |
description | Relation extraction, a fundamental task in natural language processing, aims to extract entity triples from unstructured data. These triples can then be used to build a knowledge graph. Recently, pre-training models that have learned prior semantic and syntactic knowledge, such as BERT and ERNIE, have enhanced the performance of relation extraction tasks. However, previous research has mainly focused on sequential or structural data alone, such as the shortest dependency path, ignoring the fact that fusing sequential and structural features may improve the classification performance. This study proposes a concise approach using the fused features for the relation extraction task. Firstly, for the sequential data, we verify in detail which of the generated representations can effectively improve the performance. Secondly, inspired by the pre-training task of next-sentence prediction, we propose a concise relation extraction approach based on the fusion of sequential and structural features using the pre-training model ERNIE. The experiments were conducted on the SemEval 2010 Task 8 dataset and the results show that the proposed method can improve the <i>F1</i> value to 0.902. |
first_indexed | 2024-03-11T06:13:46Z |
format | Article |
id | doaj.art-d8b99073e535484bb1dd0dc7da84c372 |
institution | Directory Open Access Journal |
issn | 2227-7390 |
language | English |
last_indexed | 2024-03-11T06:13:46Z |
publishDate | 2023-03-01 |
publisher | MDPI AG |
record_format | Article |
series | Mathematics |
spelling | doaj.art-d8b99073e535484bb1dd0dc7da84c3722023-11-17T12:28:38ZengMDPI AGMathematics2227-73902023-03-01116143910.3390/math11061439A Concise Relation Extraction Method Based on the Fusion of Sequential and Structural Features Using ERNIEYu Wang0Yuan Wang1Zhenwan Peng2Feifan Zhang3Fei Yang4School of Biomedical Engineering, Anhui Medical University, Hefei 230001, ChinaHefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230001, ChinaSchool of Biomedical Engineering, Anhui Medical University, Hefei 230001, ChinaSchool of Biomedical Engineering, Anhui Medical University, Hefei 230001, ChinaSchool of Biomedical Engineering, Anhui Medical University, Hefei 230001, ChinaRelation extraction, a fundamental task in natural language processing, aims to extract entity triples from unstructured data. These triples can then be used to build a knowledge graph. Recently, pre-training models that have learned prior semantic and syntactic knowledge, such as BERT and ERNIE, have enhanced the performance of relation extraction tasks. However, previous research has mainly focused on sequential or structural data alone, such as the shortest dependency path, ignoring the fact that fusing sequential and structural features may improve the classification performance. This study proposes a concise approach using the fused features for the relation extraction task. Firstly, for the sequential data, we verify in detail which of the generated representations can effectively improve the performance. Secondly, inspired by the pre-training task of next-sentence prediction, we propose a concise relation extraction approach based on the fusion of sequential and structural features using the pre-training model ERNIE. The experiments were conducted on the SemEval 2010 Task 8 dataset and the results show that the proposed method can improve the <i>F1</i> value to 0.902.https://www.mdpi.com/2227-7390/11/6/1439relation extractionpre-training modelsBERTERNIEshortest dependency pathfusion methods |
spellingShingle | Yu Wang Yuan Wang Zhenwan Peng Feifan Zhang Fei Yang A Concise Relation Extraction Method Based on the Fusion of Sequential and Structural Features Using ERNIE Mathematics relation extraction pre-training models BERT ERNIE shortest dependency path fusion methods |
title | A Concise Relation Extraction Method Based on the Fusion of Sequential and Structural Features Using ERNIE |
title_full | A Concise Relation Extraction Method Based on the Fusion of Sequential and Structural Features Using ERNIE |
title_fullStr | A Concise Relation Extraction Method Based on the Fusion of Sequential and Structural Features Using ERNIE |
title_full_unstemmed | A Concise Relation Extraction Method Based on the Fusion of Sequential and Structural Features Using ERNIE |
title_short | A Concise Relation Extraction Method Based on the Fusion of Sequential and Structural Features Using ERNIE |
title_sort | concise relation extraction method based on the fusion of sequential and structural features using ernie |
topic | relation extraction pre-training models BERT ERNIE shortest dependency path fusion methods |
url | https://www.mdpi.com/2227-7390/11/6/1439 |
work_keys_str_mv | AT yuwang aconciserelationextractionmethodbasedonthefusionofsequentialandstructuralfeaturesusingernie AT yuanwang aconciserelationextractionmethodbasedonthefusionofsequentialandstructuralfeaturesusingernie AT zhenwanpeng aconciserelationextractionmethodbasedonthefusionofsequentialandstructuralfeaturesusingernie AT feifanzhang aconciserelationextractionmethodbasedonthefusionofsequentialandstructuralfeaturesusingernie AT feiyang aconciserelationextractionmethodbasedonthefusionofsequentialandstructuralfeaturesusingernie AT yuwang conciserelationextractionmethodbasedonthefusionofsequentialandstructuralfeaturesusingernie AT yuanwang conciserelationextractionmethodbasedonthefusionofsequentialandstructuralfeaturesusingernie AT zhenwanpeng conciserelationextractionmethodbasedonthefusionofsequentialandstructuralfeaturesusingernie AT feifanzhang conciserelationextractionmethodbasedonthefusionofsequentialandstructuralfeaturesusingernie AT feiyang conciserelationextractionmethodbasedonthefusionofsequentialandstructuralfeaturesusingernie |