Ideal Words: A Vector-Based Formalisation of Semantic Competence
| cam.issuedOnline | 2021-05-25 | |
| dc.contributor.author | Herbelot, A | |
| dc.contributor.author | Copestake, A | |
| dc.contributor.orcid | Herbelot, A [0000-0002-4353-5908] | |
| dc.date.accessioned | 2021-11-22T14:38:32Z | |
| dc.date.available | 2021-11-22T14:38:32Z | |
| dc.date.issued | 2021 | |
| dc.date.submitted | 2020-09-14 | |
| dc.date.updated | 2021-11-22T14:38:31Z | |
| dc.description | Funder: Università degli Studi di Trento | |
| dc.description.abstract | <jats:title>Abstract</jats:title><jats:p>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.</jats:p> | |
| dc.identifier.doi | 10.17863/CAM.78268 | |
| dc.identifier.eissn | 1610-1987 | |
| dc.identifier.issn | 0933-1875 | |
| dc.identifier.other | s13218-021-00719-5 | |
| dc.identifier.other | 719 | |
| dc.identifier.uri | https://www.repository.cam.ac.uk/handle/1810/330825 | |
| dc.language | en | |
| dc.language.iso | eng | |
| dc.publisher | Springer Science and Business Media LLC | |
| dc.publisher.url | http://dx.doi.org/10.1007/s13218-021-00719-5 | |
| dc.subject | Formal semantics | |
| dc.subject | Distributional semantics | |
| dc.subject | Competence | |
| dc.title | Ideal Words: A Vector-Based Formalisation of Semantic Competence | |
| dc.type | Article | |
| dcterms.dateAccepted | 2021-04-07 | |
| prism.endingPage | 290 | |
| prism.issueIdentifier | 3-4 | |
| prism.publicationName | KI - Kunstliche Intelligenz | |
| prism.startingPage | 271 | |
| prism.volume | 35 | |
| rioxxterms.licenseref.uri | http://creativecommons.org/licenses/by/4.0/ | |
| rioxxterms.version | VoR | |
| rioxxterms.versionofrecord | 10.1007/s13218-021-00719-5 |
Files
Original bundle
1 - 2 of 2
No Thumbnail Available
- Name:
- 13218_2021_Article_719_nlm.xml
- Size:
- 421.72 KB
- Format:
- Extensible Markup Language
- Description:
- Bibliographic metadata
- Licence
- http://creativecommons.org/licenses/by/4.0/
Loading...
- Name:
- 13218_2021_Article_719.pdf
- Size:
- 2.72 MB
- Format:
- Adobe Portable Document Format
- Description:
- Published version
- Licence
- http://creativecommons.org/licenses/by/4.0/