dc.creator | Borrego Díaz, Agustín | es |
dc.creator | Ayala Hernández, Daniel | es |
dc.creator | Hernández Salmerón, Inmaculada Concepción | es |
dc.creator | Rivero, Carlos R. | es |
dc.creator | Ruiz Cortés, David | es |
dc.date.accessioned | 2021-11-04T12:03:08Z | |
dc.date.available | 2021-11-04T12:03:08Z | |
dc.date.issued | 2021 | |
dc.identifier.citation | Borrego Díaz, A., Ayala Hernández, D., Hernández Salmerón, I.C., Rivero, C.R. y Ruiz Cortés, D. (2021). CAFE: Knowledge graph completion using neighborhood-aware features. Engineering Applications of Artificial Intelligence, 103 (August 2021) | |
dc.identifier.issn | 0952-1976 | es |
dc.identifier.uri | https://hdl.handle.net/11441/127064 | |
dc.description.abstract | Knowledge Graphs (KGs) currently contain a vast amount of structured information in the form of entities
and relations. Because KGs are often constructed automatically by means of information extraction processes,
they may miss information that was either not present in the original source or not successfully extracted. As
a result, KGs might lack useful and valuable information. Current approaches that aim to complete missing
information in KGs have two main drawbacks. First, some have a dependence on embedded representations,
which impose a very expensive preprocessing step and need to be recomputed again as the KG grows. Second,
others are based on long random paths that may not cover all relevant information, whereas exhaustively
analyzing all possible paths between entities is very time-consuming. In this paper, we present an approach to
complete KGs based on evaluating candidate triples using a set of neighborhood-based features. Our approach
exploits the highly connected nature of KGs by analyzing the entities and relations surrounding any given
pair of entities, while avoiding full recomputations as new entities are added. Our results indicate that our
proposal is able to identify correct triples with a higher effectiveness than other state-of-the-art approaches,
achieving higher average F1 scores in all tested datasets. Therefore, we conclude that the information present
in the vicinities of the two entities within a candidate triple can be leveraged to determine whether that triple
is missing from the KG or not. | es |
dc.description.sponsorship | Ministerio de Economía y Competitividad TIN2016-75394-R | es |
dc.description.sponsorship | Ministerio de Ciencia, Innovación y Universidades PID2019-105471RB-I00 | es |
dc.format | application/pdf | es |
dc.format.extent | 10 | es |
dc.language.iso | eng | es |
dc.publisher | Elsevier | es |
dc.relation.ispartof | Engineering Applications of Artificial Intelligence, 103 (August 2021) | |
dc.rights | Attribution-NonCommercial-NoDerivatives 4.0 Internacional | * |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ | * |
dc.subject | Knowledge Graphs | es |
dc.subject | Knowledge Graph Completion | es |
dc.subject | Link prediction | es |
dc.subject | Machine Learning | es |
dc.title | CAFE: Knowledge graph completion using neighborhood-aware features | es |
dc.type | info:eu-repo/semantics/article | es |
dcterms.identifier | https://ror.org/03yxnpp24 | |
dc.type.version | info:eu-repo/semantics/publishedVersion | es |
dc.rights.accessRights | info:eu-repo/semantics/openAccess | es |
dc.contributor.affiliation | Universidad de Sevilla. Departamento de Lenguajes y Sistemas Informáticos | es |
dc.relation.projectID | TIN2016-75394-R | es |
dc.relation.projectID | PID2019-105471RB-I00 | es |
dc.relation.publisherversion | https://www.sciencedirect.com/science/article/pii/S0952197621001500 | es |
dc.identifier.doi | 10.1016/j.engappai.2021.104302 | es |
dc.journaltitle | Engineering Applications of Artificial Intelligence | es |
dc.publication.volumen | 103 | es |
dc.publication.issue | August 2021 | es |
dc.contributor.funder | Ministerio de Economía y Competitividad (MINECO). España | es |
dc.contributor.funder | Ministerio de Ciencia, Innovación y Universidades (MICINN). España | es |