Knowledge Graphs (KGs) are abstractions used to represent knowledge in which real-world entities are organized using a type system where types are organized using a sub-type relation: the ontology. A key factor in many applications is to evaluate the similarity between the types of the ontology. Classical measures to evaluate the semantic similarity between types are often based on the structured organization of the sub-type system. In this work, we show that it is possible to use methods coming from Natural Language Processing to embed types in a vector space starting from textual documents. We show that in this representation some of the properties of the hierarchy are still present and that the similarity in this space captures also characteristics that are close to human behavior.

Type vector representations from text: An empirical analysis / F. Bianchi, M. Soto Gomez, M. Palmonari, V. Cutrona (CEUR WORKSHOP PROCEEDINGS). - In: DL4KGS 2018 : Workshop on Deep Learning for Knowledge Graphs and Semantic Technologies 2018 / [a cura di] M. Cochez, T. Declerck, G. de Melo, L. Espinosa Anke, B. Fetahu, D. Gromann, M. Kejriwal, M. Koutraki, F. Lecue, E. Palumbo, H. Sack. - [s.l] : CEUR, 2018. - pp. 73-83 (( Intervento presentato al 1. convegno Workshop on Deep Learning for Knowledge Graphs and Semantic Technologies, DL4KGS 2018 tenutosi a Heraklion, Crete nel 2018.

Type vector representations from text: An empirical analysis

M. Soto Gomez
Secondo
;
2018

Abstract

Knowledge Graphs (KGs) are abstractions used to represent knowledge in which real-world entities are organized using a type system where types are organized using a sub-type relation: the ontology. A key factor in many applications is to evaluate the similarity between the types of the ontology. Classical measures to evaluate the semantic similarity between types are often based on the structured organization of the sub-type system. In this work, we show that it is possible to use methods coming from Natural Language Processing to embed types in a vector space starting from textual documents. We show that in this representation some of the properties of the hierarchy are still present and that the similarity in this space captures also characteristics that are close to human behavior.
Settore INF/01 - Informatica
2018
https://ceur-ws.org/Vol-2106/paper9.pdf
Book Part (author)
File in questo prodotto:
File Dimensione Formato  
12_2018_Type vector representations from text.pdf

accesso aperto

Tipologia: Publisher's version/PDF
Dimensione 613.95 kB
Formato Adobe PDF
613.95 kB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2434/961507
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? ND
social impact