%0 Journal Article %1 herbelot2021ideal %A Herbelot, Aurélie %A Copestake, Ann A. %D 2021 %J KI - Künstliche Intelligenz %K artificial_intelligence competence distributional_semantics formal_semantics natural_language_processing semantics %N 3 %P 271--290 %R 10.1007/s13218-021-00719-5 %T Ideal Words: A Vector-Based Formalisation of Semantic Competence %U https://link.springer.com/article/10.1007/s13218-021-00719-5 %V 35 %X 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.

@article{herbelot2021ideal, 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.}, added-at = {2025-04-17T10:16:01.000+0200}, author = {Herbelot, Aurélie and Copestake, Ann A.}, biburl = {https://www.bibsonomy.org/bibtex/2e40d6e15a3bf3be39c81179515f3822a/meneteqel}, day = 1, doi = {10.1007/s13218-021-00719-5}, interhash = {3b16481d950dfa101b567d689b1cd6fa}, intrahash = {e40d6e15a3bf3be39c81179515f3822a}, issn = {1610-1987}, journal = {KI - Künstliche Intelligenz}, keywords = {artificial_intelligence competence distributional_semantics formal_semantics natural_language_processing semantics}, language = {en}, month = nov, number = 3, pages = {271--290}, timestamp = {2025-04-17T10:16:01.000+0200}, title = {Ideal Words: A Vector-Based Formalisation of Semantic Competence}, url = {https://link.springer.com/article/10.1007/s13218-021-00719-5}, volume = 35, year = 2021 }