6533b7ddfe1ef96bd127485f
RESEARCH PRODUCT
A First Experiment on Including Text Literals in KGloVe
Michael CochezMartina GarofaloJérôme LenßenMaria Angela Pellegrinosubject
FOS: Computer and information sciencesgraph embeddingsComputer Science - Computation and LanguageArtificial Intelligence (cs.AI)koneoppiminenknowledge graphComputer Science - Artificial IntelligencetekstinlouhintaattributestiedonlouhintaComputation and Language (cs.CL)description
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.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2018-07-31 |