In this paper we introduce a system for the computation of explanations that accompany scores in the conceptual similarity task. In this setting the problem is, given a pair of concepts, to provide a score that expresses in how far the two concepts are similar. In order to explain how explanations are automatically built, we illustrate some basic features of COVER, the lexical resource that underlies our approach, and the main traits of the MeRaLi system, that computes conceptual similarity and explanations, all in one. To assess the computed explanations, we have designed a human experimentation, that provided interesting and encouraging results, which we report and discuss in depth.

Tell me why: Computational explanation of conceptual similarity judgment

Davide Colla;Enrico Mensa;Daniele P. Radicioni;Antonio Lieto
2018-01-01

Abstract

In this paper we introduce a system for the computation of explanations that accompany scores in the conceptual similarity task. In this setting the problem is, given a pair of concepts, to provide a score that expresses in how far the two concepts are similar. In order to explain how explanations are automatically built, we illustrate some basic features of COVER, the lexical resource that underlies our approach, and the main traits of the MeRaLi system, that computes conceptual similarity and explanations, all in one. To assess the computed explanations, we have designed a human experimentation, that provided interesting and encouraging results, which we report and discuss in depth.
2018
17th International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems, IPMU 2018
Cadiz; Spain
June, 11-15, 2018
Information Processing and Management of Uncertainty in Knowledge-Based Systems. Theory and Foundations
Springer Nature
74-85
74
85
978-3-319-91472-5
https://link.springer.com/chapter/10.1007/978-3-319-91473-2_7
Explanation, Lexical semantics, Natural language semantics, Conceptual similarity, Lexical resources
Davide Colla, Enrico Mensa, Daniele P. Radicioni, Antonio Lieto
File in questo prodotto:
File Dimensione Formato  
colla2018tell.pdf

Accesso aperto

Tipo di file: POSTPRINT (VERSIONE FINALE DELL’AUTORE)
Dimensione 8.24 MB
Formato Adobe PDF
8.24 MB Adobe PDF Visualizza/Apri

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/2318/1685422
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 8
  • ???jsp.display-item.citation.isi??? 4
social impact