Confidence-Aware Embedding for Knowledge Graph Entity Typing
Knowledge graphs (KGs) entity typing aims to predict the potential types to an entity, that is, (entity, entity type = ?). Recently, several embedding models are proposed for KG entity types prediction according to the existing typing information of the (entity, entity type) tuples in KGs. However,...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi-Wiley
2021-01-01
|
Series: | Complexity |
Online Access: | http://dx.doi.org/10.1155/2021/3473849 |
id |
doaj-b8ea826267b54dc5932a9db8e44d0f62 |
---|---|
record_format |
Article |
spelling |
doaj-b8ea826267b54dc5932a9db8e44d0f622021-04-26T00:05:02ZengHindawi-WileyComplexity1099-05262021-01-01202110.1155/2021/3473849Confidence-Aware Embedding for Knowledge Graph Entity TypingYu Zhao0Jiayue Hou1Zongjian Yu2Yun Zhang3Qing Li4Fintech Innovation CenterFintech Innovation CenterFintech Innovation CenterFintech Innovation CenterFintech Innovation CenterKnowledge graphs (KGs) entity typing aims to predict the potential types to an entity, that is, (entity, entity type = ?). Recently, several embedding models are proposed for KG entity types prediction according to the existing typing information of the (entity, entity type) tuples in KGs. However, most of them unreasonably assume that all existing entity typing instances in KGs are completely correct, which ignore the nonnegligible entity type noises and may lead to potential errors for the downstream tasks. To address this problem, we propose ConfE, a novel confidence-aware embedding approach for modeling the (entity, entity type) tuples, which takes tuple confidence into consideration for learning better embeddings. Specifically, we learn the embeddings of entities and entity types in separate entity space and entity type space since they are different objects in KGs. We utilize an asymmetric matrix to specify the interaction of their embeddings and incorporate the tuple confidence as well. To make the tuple confidence more universal, we consider only the internal structural information in existing KGs. We evaluate our model on two tasks, including entity type noise detection and entity type prediction. The extensive experimental results in two public benchmark datasets (i.e., FB15kET and YAGO43kET) demonstrate that our proposed model outperforms all baselines on all tasks, which verify the effectiveness of ConfE in learning better embeddings on noisy KGs. The source code and data of this work can be obtained from https://github.com/swufenlp/ConfE.http://dx.doi.org/10.1155/2021/3473849 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yu Zhao Jiayue Hou Zongjian Yu Yun Zhang Qing Li |
spellingShingle |
Yu Zhao Jiayue Hou Zongjian Yu Yun Zhang Qing Li Confidence-Aware Embedding for Knowledge Graph Entity Typing Complexity |
author_facet |
Yu Zhao Jiayue Hou Zongjian Yu Yun Zhang Qing Li |
author_sort |
Yu Zhao |
title |
Confidence-Aware Embedding for Knowledge Graph Entity Typing |
title_short |
Confidence-Aware Embedding for Knowledge Graph Entity Typing |
title_full |
Confidence-Aware Embedding for Knowledge Graph Entity Typing |
title_fullStr |
Confidence-Aware Embedding for Knowledge Graph Entity Typing |
title_full_unstemmed |
Confidence-Aware Embedding for Knowledge Graph Entity Typing |
title_sort |
confidence-aware embedding for knowledge graph entity typing |
publisher |
Hindawi-Wiley |
series |
Complexity |
issn |
1099-0526 |
publishDate |
2021-01-01 |
description |
Knowledge graphs (KGs) entity typing aims to predict the potential types to an entity, that is, (entity, entity type = ?). Recently, several embedding models are proposed for KG entity types prediction according to the existing typing information of the (entity, entity type) tuples in KGs. However, most of them unreasonably assume that all existing entity typing instances in KGs are completely correct, which ignore the nonnegligible entity type noises and may lead to potential errors for the downstream tasks. To address this problem, we propose ConfE, a novel confidence-aware embedding approach for modeling the (entity, entity type) tuples, which takes tuple confidence into consideration for learning better embeddings. Specifically, we learn the embeddings of entities and entity types in separate entity space and entity type space since they are different objects in KGs. We utilize an asymmetric matrix to specify the interaction of their embeddings and incorporate the tuple confidence as well. To make the tuple confidence more universal, we consider only the internal structural information in existing KGs. We evaluate our model on two tasks, including entity type noise detection and entity type prediction. The extensive experimental results in two public benchmark datasets (i.e., FB15kET and YAGO43kET) demonstrate that our proposed model outperforms all baselines on all tasks, which verify the effectiveness of ConfE in learning better embeddings on noisy KGs. The source code and data of this work can be obtained from https://github.com/swufenlp/ConfE. |
url |
http://dx.doi.org/10.1155/2021/3473849 |
work_keys_str_mv |
AT yuzhao confidenceawareembeddingforknowledgegraphentitytyping AT jiayuehou confidenceawareembeddingforknowledgegraphentitytyping AT zongjianyu confidenceawareembeddingforknowledgegraphentitytyping AT yunzhang confidenceawareembeddingforknowledgegraphentitytyping AT qingli confidenceawareembeddingforknowledgegraphentitytyping |
_version_ |
1714657478034063360 |