Cargando…
Multi-Task Learning and Improved TextRank for Knowledge Graph Completion
Knowledge graph completion is an important technology for supplementing knowledge graphs and improving data quality. However, the existing knowledge graph completion methods ignore the features of triple relations, and the introduced entity description texts are long and redundant. To address these...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9601466/ https://www.ncbi.nlm.nih.gov/pubmed/37420516 http://dx.doi.org/10.3390/e24101495 |
_version_ | 1784817072490938368 |
---|---|
author | Tian, Hao Zhang, Xiaoxiong Wang, Yuhan Zeng, Daojian |
author_facet | Tian, Hao Zhang, Xiaoxiong Wang, Yuhan Zeng, Daojian |
author_sort | Tian, Hao |
collection | PubMed |
description | Knowledge graph completion is an important technology for supplementing knowledge graphs and improving data quality. However, the existing knowledge graph completion methods ignore the features of triple relations, and the introduced entity description texts are long and redundant. To address these problems, this study proposes a multi-task learning and improved TextRank for knowledge graph completion (MIT-KGC) model. The key contexts are first extracted from redundant entity descriptions using the improved TextRank algorithm. Then, a lite bidirectional encoder representations from transformers (ALBERT) is used as the text encoder to reduce the parameters of the model. Subsequently, the multi-task learning method is utilized to fine-tune the model by effectively integrating the entity and relation features. Based on the datasets of WN18RR, FB15k-237, and DBpedia50k, experiments were conducted with the proposed model and the results showed that, compared with traditional methods, the mean rank (MR), top 10 hit ratio (Hit@10), and top three hit ratio (Hit@3) were enhanced by 38, 1.3%, and 1.9%, respectively, on WN18RR. Additionally, the MR and Hit@10 were increased by 23 and 0.7%, respectively, on FB15k-237. The model also improved the Hit@3 and the top one hit ratio (Hit@1) by 3.1% and 1.5% on the dataset DBpedia50k, respectively, verifying the validity of the model. |
format | Online Article Text |
id | pubmed-9601466 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-96014662022-10-27 Multi-Task Learning and Improved TextRank for Knowledge Graph Completion Tian, Hao Zhang, Xiaoxiong Wang, Yuhan Zeng, Daojian Entropy (Basel) Article Knowledge graph completion is an important technology for supplementing knowledge graphs and improving data quality. However, the existing knowledge graph completion methods ignore the features of triple relations, and the introduced entity description texts are long and redundant. To address these problems, this study proposes a multi-task learning and improved TextRank for knowledge graph completion (MIT-KGC) model. The key contexts are first extracted from redundant entity descriptions using the improved TextRank algorithm. Then, a lite bidirectional encoder representations from transformers (ALBERT) is used as the text encoder to reduce the parameters of the model. Subsequently, the multi-task learning method is utilized to fine-tune the model by effectively integrating the entity and relation features. Based on the datasets of WN18RR, FB15k-237, and DBpedia50k, experiments were conducted with the proposed model and the results showed that, compared with traditional methods, the mean rank (MR), top 10 hit ratio (Hit@10), and top three hit ratio (Hit@3) were enhanced by 38, 1.3%, and 1.9%, respectively, on WN18RR. Additionally, the MR and Hit@10 were increased by 23 and 0.7%, respectively, on FB15k-237. The model also improved the Hit@3 and the top one hit ratio (Hit@1) by 3.1% and 1.5% on the dataset DBpedia50k, respectively, verifying the validity of the model. MDPI 2022-10-20 /pmc/articles/PMC9601466/ /pubmed/37420516 http://dx.doi.org/10.3390/e24101495 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Tian, Hao Zhang, Xiaoxiong Wang, Yuhan Zeng, Daojian Multi-Task Learning and Improved TextRank for Knowledge Graph Completion |
title | Multi-Task Learning and Improved TextRank for Knowledge Graph Completion |
title_full | Multi-Task Learning and Improved TextRank for Knowledge Graph Completion |
title_fullStr | Multi-Task Learning and Improved TextRank for Knowledge Graph Completion |
title_full_unstemmed | Multi-Task Learning and Improved TextRank for Knowledge Graph Completion |
title_short | Multi-Task Learning and Improved TextRank for Knowledge Graph Completion |
title_sort | multi-task learning and improved textrank for knowledge graph completion |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9601466/ https://www.ncbi.nlm.nih.gov/pubmed/37420516 http://dx.doi.org/10.3390/e24101495 |
work_keys_str_mv | AT tianhao multitasklearningandimprovedtextrankforknowledgegraphcompletion AT zhangxiaoxiong multitasklearningandimprovedtextrankforknowledgegraphcompletion AT wangyuhan multitasklearningandimprovedtextrankforknowledgegraphcompletion AT zengdaojian multitasklearningandimprovedtextrankforknowledgegraphcompletion |