In this theoretical paper, we consider the notion of semantic competence and its relation to general language understanding—one of the most sough-after goals of Artificial Intelligence. We come back to three main accounts of competence involving (a) lexical knowledge; (b) truth-theoretic reference; and (c) causal chains in language use. We argue that all three are needed to reach a notion of meaning in artificial agents and suggest that they can be combined in a single formalisation, where competence develops from exposure to observable performance data. We introduce a theoretical framework which translates set theory into vector-space semantics by applying distributional techniques to a corpus of utterances associated with truth values. The resulting meaning space naturally satisfies the requirements of a causal theory of competence, but it can also be regarded as some ‘ideal’ model of the world, allowing for extensions and standard lexical relations to be retrieved.

Ideal Words: A Vector-Based Formalisation of Semantic Competence / Herbelot, A.; Copestake, A.. - In: KI - KÜNSTLICHE INTELLIGENZ. - ISSN 0933-1875. - 2021/35:3-4(2021), pp. 271-290. [10.1007/s13218-021-00719-5]

Ideal Words: A Vector-Based Formalisation of Semantic Competence

Herbelot A.;
2021-01-01

Abstract

In this theoretical paper, we consider the notion of semantic competence and its relation to general language understanding—one of the most sough-after goals of Artificial Intelligence. We come back to three main accounts of competence involving (a) lexical knowledge; (b) truth-theoretic reference; and (c) causal chains in language use. We argue that all three are needed to reach a notion of meaning in artificial agents and suggest that they can be combined in a single formalisation, where competence develops from exposure to observable performance data. We introduce a theoretical framework which translates set theory into vector-space semantics by applying distributional techniques to a corpus of utterances associated with truth values. The resulting meaning space naturally satisfies the requirements of a causal theory of competence, but it can also be regarded as some ‘ideal’ model of the world, allowing for extensions and standard lexical relations to be retrieved.
2021
3-4
Herbelot, A.; Copestake, A.
Ideal Words: A Vector-Based Formalisation of Semantic Competence / Herbelot, A.; Copestake, A.. - In: KI - KÜNSTLICHE INTELLIGENZ. - ISSN 0933-1875. - 2021/35:3-4(2021), pp. 271-290. [10.1007/s13218-021-00719-5]
File in questo prodotto:
File Dimensione Formato  
Ideal_Words___final_version.pdf

accesso aperto

Tipologia: Post-print referato (Refereed author’s manuscript)
Licenza: Creative commons
Dimensione 724.1 kB
Formato Adobe PDF
724.1 kB Adobe PDF Visualizza/Apri
Herbelot-Copestake2021_Article_IdealWords.pdf

accesso aperto

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Creative commons
Dimensione 2.79 MB
Formato Adobe PDF
2.79 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/11572/313864
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? 4
social impact