An Entity Relation Extraction Method Based on Dynamic Context and Multi-Feature Fusion
Dynamic context selector, a kind of mask idea, will divide the matrix into some regions, selecting the information of region as the input of model dynamically. There is a novel thought that improvement is made on the entity relation extraction (ERE) by applying the dynamic context to the training. I...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-01-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/12/3/1532 |
_version_ | 1797489094344835072 |
---|---|
author | Xiaolin Ma Kaiqi Wu Hailan Kuang Xinhua Liu |
author_facet | Xiaolin Ma Kaiqi Wu Hailan Kuang Xinhua Liu |
author_sort | Xiaolin Ma |
collection | DOAJ |
description | Dynamic context selector, a kind of mask idea, will divide the matrix into some regions, selecting the information of region as the input of model dynamically. There is a novel thought that improvement is made on the entity relation extraction (ERE) by applying the dynamic context to the training. In reality, most existing models of joint extraction of entity and relation are based on static context, which always suffers from the feature missing issue, resulting in poor performance. To address the problem, we propose a span-based joint extraction method based on dynamic context and multi-feature fusion (SPERT-DC). The context area is picked dynamically with the help of threshold in feature selecting layer of the model. It is noted that we also use Bi-LSTM_ATT to improve compatibility of longer text in feature extracting layer and enhance context information by combining with the tags of entity in feature fusion layer. Furthermore, the model in this paper outperforms prior work by up to 1% F1 score on the public dataset, which has verified the efficiency of dynamic context on ERE model. |
first_indexed | 2024-03-10T00:11:35Z |
format | Article |
id | doaj.art-ebb64deabd13480598d592852e2beca6 |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-10T00:11:35Z |
publishDate | 2022-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-ebb64deabd13480598d592852e2beca62023-11-23T15:59:10ZengMDPI AGApplied Sciences2076-34172022-01-01123153210.3390/app12031532An Entity Relation Extraction Method Based on Dynamic Context and Multi-Feature FusionXiaolin Ma0Kaiqi Wu1Hailan Kuang2Xinhua Liu3Hubei Key Laboratory of Broadband Wireless Communication and Sensor Networks, School of Information Engineering, Wuhan University of Technology, Wuhan 430070, ChinaHubei Key Laboratory of Broadband Wireless Communication and Sensor Networks, School of Information Engineering, Wuhan University of Technology, Wuhan 430070, ChinaHubei Key Laboratory of Broadband Wireless Communication and Sensor Networks, School of Information Engineering, Wuhan University of Technology, Wuhan 430070, ChinaHubei Key Laboratory of Broadband Wireless Communication and Sensor Networks, School of Information Engineering, Wuhan University of Technology, Wuhan 430070, ChinaDynamic context selector, a kind of mask idea, will divide the matrix into some regions, selecting the information of region as the input of model dynamically. There is a novel thought that improvement is made on the entity relation extraction (ERE) by applying the dynamic context to the training. In reality, most existing models of joint extraction of entity and relation are based on static context, which always suffers from the feature missing issue, resulting in poor performance. To address the problem, we propose a span-based joint extraction method based on dynamic context and multi-feature fusion (SPERT-DC). The context area is picked dynamically with the help of threshold in feature selecting layer of the model. It is noted that we also use Bi-LSTM_ATT to improve compatibility of longer text in feature extracting layer and enhance context information by combining with the tags of entity in feature fusion layer. Furthermore, the model in this paper outperforms prior work by up to 1% F1 score on the public dataset, which has verified the efficiency of dynamic context on ERE model.https://www.mdpi.com/2076-3417/12/3/1532mask selectorrelation extractionattention mechanismthresholdmulti-feature fusion |
spellingShingle | Xiaolin Ma Kaiqi Wu Hailan Kuang Xinhua Liu An Entity Relation Extraction Method Based on Dynamic Context and Multi-Feature Fusion Applied Sciences mask selector relation extraction attention mechanism threshold multi-feature fusion |
title | An Entity Relation Extraction Method Based on Dynamic Context and Multi-Feature Fusion |
title_full | An Entity Relation Extraction Method Based on Dynamic Context and Multi-Feature Fusion |
title_fullStr | An Entity Relation Extraction Method Based on Dynamic Context and Multi-Feature Fusion |
title_full_unstemmed | An Entity Relation Extraction Method Based on Dynamic Context and Multi-Feature Fusion |
title_short | An Entity Relation Extraction Method Based on Dynamic Context and Multi-Feature Fusion |
title_sort | entity relation extraction method based on dynamic context and multi feature fusion |
topic | mask selector relation extraction attention mechanism threshold multi-feature fusion |
url | https://www.mdpi.com/2076-3417/12/3/1532 |
work_keys_str_mv | AT xiaolinma anentityrelationextractionmethodbasedondynamiccontextandmultifeaturefusion AT kaiqiwu anentityrelationextractionmethodbasedondynamiccontextandmultifeaturefusion AT hailankuang anentityrelationextractionmethodbasedondynamiccontextandmultifeaturefusion AT xinhualiu anentityrelationextractionmethodbasedondynamiccontextandmultifeaturefusion AT xiaolinma entityrelationextractionmethodbasedondynamiccontextandmultifeaturefusion AT kaiqiwu entityrelationextractionmethodbasedondynamiccontextandmultifeaturefusion AT hailankuang entityrelationextractionmethodbasedondynamiccontextandmultifeaturefusion AT xinhualiu entityrelationextractionmethodbasedondynamiccontextandmultifeaturefusion |