Entity Linking via Symmetrical Attention-Based Neural Network and Entity Structural Features
In the process of knowledge graph construction, entity linking is a pivotal step, which maps mentions in text to a knowledge base. Existing models only utilize individual information to represent their latent features and ignore the correlation between entities and their mentions. Besides, in the pr...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-04-01
|
Series: | Symmetry |
Subjects: | |
Online Access: | https://www.mdpi.com/2073-8994/11/4/453 |
id |
doaj-01e4fc54293a4577b81e00efadf53299 |
---|---|
record_format |
Article |
spelling |
doaj-01e4fc54293a4577b81e00efadf532992020-11-24T20:54:35ZengMDPI AGSymmetry2073-89942019-04-0111445310.3390/sym11040453sym11040453Entity Linking via Symmetrical Attention-Based Neural Network and Entity Structural FeaturesShengze Hu0Zhen Tan1Weixin Zeng2Bin Ge3Weidong Xiao4Science and Technology on Information Systems Engineering Laboratory, National University of Defense Technology, Changsha 410073, ChinaScience and Technology on Information Systems Engineering Laboratory, National University of Defense Technology, Changsha 410073, ChinaScience and Technology on Information Systems Engineering Laboratory, National University of Defense Technology, Changsha 410073, ChinaScience and Technology on Information Systems Engineering Laboratory, National University of Defense Technology, Changsha 410073, ChinaScience and Technology on Information Systems Engineering Laboratory, National University of Defense Technology, Changsha 410073, ChinaIn the process of knowledge graph construction, entity linking is a pivotal step, which maps mentions in text to a knowledge base. Existing models only utilize individual information to represent their latent features and ignore the correlation between entities and their mentions. Besides, in the process of entity feature extraction, only partial latent features, i.e., context features, are leveraged to extract latent features, and the pivotal entity structural features are ignored. In this paper, we propose SA-ESF, which leverages the symmetrical Bi-LSTM neural network with the double attention mechanism to calculate the correlation between mentions and entities in two aspects: (1) entity embeddings and mention context features; (2) mention embeddings and entity description features; furthermore, the context features, structural features, and entity ID feature are integrated to represent entity embeddings jointly. Finally, we leverage (1) the similarity score between each mention and its candidate entities and (2) the prior probability to calculate the final ranking results. The experimental results on nine benchmark dataset validate the performance of SA-ESF where the average F1 score is up to 0.866.https://www.mdpi.com/2073-8994/11/4/453symmetrical neural networkentity linkingentity structural featuresprior probabilityinformation integration |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Shengze Hu Zhen Tan Weixin Zeng Bin Ge Weidong Xiao |
spellingShingle |
Shengze Hu Zhen Tan Weixin Zeng Bin Ge Weidong Xiao Entity Linking via Symmetrical Attention-Based Neural Network and Entity Structural Features Symmetry symmetrical neural network entity linking entity structural features prior probability information integration |
author_facet |
Shengze Hu Zhen Tan Weixin Zeng Bin Ge Weidong Xiao |
author_sort |
Shengze Hu |
title |
Entity Linking via Symmetrical Attention-Based Neural Network and Entity Structural Features |
title_short |
Entity Linking via Symmetrical Attention-Based Neural Network and Entity Structural Features |
title_full |
Entity Linking via Symmetrical Attention-Based Neural Network and Entity Structural Features |
title_fullStr |
Entity Linking via Symmetrical Attention-Based Neural Network and Entity Structural Features |
title_full_unstemmed |
Entity Linking via Symmetrical Attention-Based Neural Network and Entity Structural Features |
title_sort |
entity linking via symmetrical attention-based neural network and entity structural features |
publisher |
MDPI AG |
series |
Symmetry |
issn |
2073-8994 |
publishDate |
2019-04-01 |
description |
In the process of knowledge graph construction, entity linking is a pivotal step, which maps mentions in text to a knowledge base. Existing models only utilize individual information to represent their latent features and ignore the correlation between entities and their mentions. Besides, in the process of entity feature extraction, only partial latent features, i.e., context features, are leveraged to extract latent features, and the pivotal entity structural features are ignored. In this paper, we propose SA-ESF, which leverages the symmetrical Bi-LSTM neural network with the double attention mechanism to calculate the correlation between mentions and entities in two aspects: (1) entity embeddings and mention context features; (2) mention embeddings and entity description features; furthermore, the context features, structural features, and entity ID feature are integrated to represent entity embeddings jointly. Finally, we leverage (1) the similarity score between each mention and its candidate entities and (2) the prior probability to calculate the final ranking results. The experimental results on nine benchmark dataset validate the performance of SA-ESF where the average F1 score is up to 0.866. |
topic |
symmetrical neural network entity linking entity structural features prior probability information integration |
url |
https://www.mdpi.com/2073-8994/11/4/453 |
work_keys_str_mv |
AT shengzehu entitylinkingviasymmetricalattentionbasedneuralnetworkandentitystructuralfeatures AT zhentan entitylinkingviasymmetricalattentionbasedneuralnetworkandentitystructuralfeatures AT weixinzeng entitylinkingviasymmetricalattentionbasedneuralnetworkandentitystructuralfeatures AT binge entitylinkingviasymmetricalattentionbasedneuralnetworkandentitystructuralfeatures AT weidongxiao entitylinkingviasymmetricalattentionbasedneuralnetworkandentitystructuralfeatures |
_version_ |
1716793995092295680 |