A first experiment on including text literals in KGlove

Michael Cochez, Martina Garofalo, Jérôme Lenßen, Maria Angela Pellegrino

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

Abstract

Graph embedding models produce embedding vectors for entities and relations in Knowledge Graphs, often without taking literal properties into account. We show an initial idea based on the combination of global graph structure with additional information provided by textual information in properties. Our initial experiment shows that this approach might be useful, but does not clearly outperform earlier approaches when evaluated on machine learning tasks.

Original languageEnglish
Title of host publicationJoint 4th Workshop on Semantic Deep Learning: Natural Language Interfaces for the Web of Data and 9th Question Answering over Linked Data Challenge, SemDeep-4_NLIWOD-4 2018
Pages103-106
Number of pages4
Volume2241
Publication statusPublished - 1 Jan 2018
Externally publishedYes
EventJoint 4th Workshop on Semantic Deep Learning: Natural Language Interfaces for the Web of Data and 9th Question Answering over Linked Data Challenge, SemDeep-4_NLIWOD-4 2018 - Monterey, United States
Duration: 8 Oct 20189 Oct 2018

Publication series

NameCEUR Workshop Proceedings
PublisherCEUR Workshop Proceedings
ISSN (Print)1613-0073

Conference

ConferenceJoint 4th Workshop on Semantic Deep Learning: Natural Language Interfaces for the Web of Data and 9th Question Answering over Linked Data Challenge, SemDeep-4_NLIWOD-4 2018
CountryUnited States
CityMonterey
Period8/10/189/10/18

Keywords

  • Attributes
  • Graph embeddings
  • Knowledge graph

Fingerprint

Dive into the research topics of 'A first experiment on including text literals in KGlove'. Together they form a unique fingerprint.

Cite this