Path-based knowledge reasoning with textual semantic information for medical knowledge graph completion

Abstract Background Knowledge graphs (KGs), especially medical knowledge graphs, are often significantly incomplete, so it necessitating a demand for medical knowledge graph completion (MedKGC). MedKGC can find new facts based on the existed knowledge in the KGs. The path-based knowledge reasoning a...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yinyu Lan, Shizhu He, Kang Liu, Xiangrong Zeng, Shengping Liu, Jun Zhao
Formato:	article
Lenguaje:	EN
Publicado:	BMC 2021
Materias:	Medical knowledge graph completion Path-based knowledge reasoning Textual semantic representation Pre-trained language model Computer applications to medicine. Medical informatics R858-859.7
Acceso en línea:	https://doaj.org/article/0fa7a223b3bf420488480ddd08c842d1
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:0fa7a223b3bf420488480ddd08c842d1
record_format	dspace
spelling	oai:doaj.org-article:0fa7a223b3bf420488480ddd08c842d12021-12-05T12:18:59ZPath-based knowledge reasoning with textual semantic information for medical knowledge graph completion10.1186/s12911-021-01622-71472-6947https://doaj.org/article/0fa7a223b3bf420488480ddd08c842d12021-11-01T00:00:00Zhttps://doi.org/10.1186/s12911-021-01622-7https://doaj.org/toc/1472-6947Abstract Background Knowledge graphs (KGs), especially medical knowledge graphs, are often significantly incomplete, so it necessitating a demand for medical knowledge graph completion (MedKGC). MedKGC can find new facts based on the existed knowledge in the KGs. The path-based knowledge reasoning algorithm is one of the most important approaches to this task. This type of method has received great attention in recent years because of its high performance and interpretability. In fact, traditional methods such as path ranking algorithm take the paths between an entity pair as atomic features. However, the medical KGs are very sparse, which makes it difficult to model effective semantic representation for extremely sparse path features. The sparsity in the medical KGs is mainly reflected in the long-tailed distribution of entities and paths. Previous methods merely consider the context structure in the paths of knowledge graph and ignore the textual semantics of the symbols in the path. Therefore, their performance cannot be further improved due to the two aspects of entity sparseness and path sparseness. Methods To address the above issues, this paper proposes two novel path-based reasoning methods to solve the sparsity issues of entity and path respectively, which adopts the textual semantic information of entities and paths for MedKGC. By using the pre-trained model BERT, combining the textual semantic representations of the entities and the relationships, we model the task of symbolic reasoning in the medical KG as a numerical computing issue in textual semantic representation. Results Experiments results on the publicly authoritative Chinese symptom knowledge graph demonstrated that the proposed method is significantly better than the state-of-the-art path-based knowledge graph reasoning methods, and the average performance is improved by 5.83% for all relations. Conclusions In this paper, we propose two new knowledge graph reasoning algorithms, which adopt textual semantic information of entities and paths and can effectively alleviate the sparsity problem of entities and paths in the MedKGC. As far as we know, it is the first method to use pre-trained language models and text path representations for medical knowledge reasoning. Our method can complete the impaired symptom knowledge graph in an interpretable way, and it outperforms the state-of-the-art path-based reasoning methods.Yinyu LanShizhu HeKang LiuXiangrong ZengShengping LiuJun ZhaoBMCarticleMedical knowledge graph completionPath-based knowledge reasoningTextual semantic representationPre-trained language modelComputer applications to medicine. Medical informaticsR858-859.7ENBMC Medical Informatics and Decision Making, Vol 21, Iss S9, Pp 1-12 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medical knowledge graph completion Path-based knowledge reasoning Textual semantic representation Pre-trained language model Computer applications to medicine. Medical informatics R858-859.7
spellingShingle	Medical knowledge graph completion Path-based knowledge reasoning Textual semantic representation Pre-trained language model Computer applications to medicine. Medical informatics R858-859.7 Yinyu Lan Shizhu He Kang Liu Xiangrong Zeng Shengping Liu Jun Zhao Path-based knowledge reasoning with textual semantic information for medical knowledge graph completion
description	Abstract Background Knowledge graphs (KGs), especially medical knowledge graphs, are often significantly incomplete, so it necessitating a demand for medical knowledge graph completion (MedKGC). MedKGC can find new facts based on the existed knowledge in the KGs. The path-based knowledge reasoning algorithm is one of the most important approaches to this task. This type of method has received great attention in recent years because of its high performance and interpretability. In fact, traditional methods such as path ranking algorithm take the paths between an entity pair as atomic features. However, the medical KGs are very sparse, which makes it difficult to model effective semantic representation for extremely sparse path features. The sparsity in the medical KGs is mainly reflected in the long-tailed distribution of entities and paths. Previous methods merely consider the context structure in the paths of knowledge graph and ignore the textual semantics of the symbols in the path. Therefore, their performance cannot be further improved due to the two aspects of entity sparseness and path sparseness. Methods To address the above issues, this paper proposes two novel path-based reasoning methods to solve the sparsity issues of entity and path respectively, which adopts the textual semantic information of entities and paths for MedKGC. By using the pre-trained model BERT, combining the textual semantic representations of the entities and the relationships, we model the task of symbolic reasoning in the medical KG as a numerical computing issue in textual semantic representation. Results Experiments results on the publicly authoritative Chinese symptom knowledge graph demonstrated that the proposed method is significantly better than the state-of-the-art path-based knowledge graph reasoning methods, and the average performance is improved by 5.83% for all relations. Conclusions In this paper, we propose two new knowledge graph reasoning algorithms, which adopt textual semantic information of entities and paths and can effectively alleviate the sparsity problem of entities and paths in the MedKGC. As far as we know, it is the first method to use pre-trained language models and text path representations for medical knowledge reasoning. Our method can complete the impaired symptom knowledge graph in an interpretable way, and it outperforms the state-of-the-art path-based reasoning methods.
format	article
author	Yinyu Lan Shizhu He Kang Liu Xiangrong Zeng Shengping Liu Jun Zhao
author_facet	Yinyu Lan Shizhu He Kang Liu Xiangrong Zeng Shengping Liu Jun Zhao
author_sort	Yinyu Lan
title	Path-based knowledge reasoning with textual semantic information for medical knowledge graph completion
title_short	Path-based knowledge reasoning with textual semantic information for medical knowledge graph completion
title_full	Path-based knowledge reasoning with textual semantic information for medical knowledge graph completion
title_fullStr	Path-based knowledge reasoning with textual semantic information for medical knowledge graph completion
title_full_unstemmed	Path-based knowledge reasoning with textual semantic information for medical knowledge graph completion
title_sort	path-based knowledge reasoning with textual semantic information for medical knowledge graph completion
publisher	BMC
publishDate	2021
url	https://doaj.org/article/0fa7a223b3bf420488480ddd08c842d1
work_keys_str_mv	AT yinyulan pathbasedknowledgereasoningwithtextualsemanticinformationformedicalknowledgegraphcompletion AT shizhuhe pathbasedknowledgereasoningwithtextualsemanticinformationformedicalknowledgegraphcompletion AT kangliu pathbasedknowledgereasoningwithtextualsemanticinformationformedicalknowledgegraphcompletion AT xiangrongzeng pathbasedknowledgereasoningwithtextualsemanticinformationformedicalknowledgegraphcompletion AT shengpingliu pathbasedknowledgereasoningwithtextualsemanticinformationformedicalknowledgegraphcompletion AT junzhao pathbasedknowledgereasoningwithtextualsemanticinformationformedicalknowledgegraphcompletion
_version_	1718372058722729984

Path-based knowledge reasoning with textual semantic information for medical knowledge graph completion

Ejemplares similares