Lexical Semantics with Vector Symbolic Architectures

Adam Roussel


Abstract
Conventional approaches to the construction of word vectors typically require very large amounts of unstructured text and powerful computing hardware, and the vectors themselves are also difficult if not impossible to inspect or interpret on their own. In this paper, we introduce a method for building word vectors using the framework of vector symbolic architectures in order to encode the semantic information in wordnets, such as the Open English WordNet or the Open Multilingual Wordnet. Such vectors perform surprisingly well on common word similarity benchmarks, and yet they are transparent, interpretable, and the information contained within them has a clear provenance.
Anthology ID:
2023.resourceful-1.8
Volume:
Proceedings of the Second Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2023)
Month:
May
Year:
2023
Address:
Tórshavn, the Faroe Islands
Editors:
Nikolai Ilinykh, Felix Morger, Dana Dannélls, Simon Dobnik, Beáta Megyesi, Joakim Nivre
Venue:
RESOURCEFUL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
53–61
Language:
URL:
https://aclanthology.org/2023.resourceful-1.8
DOI:
Bibkey:
Cite (ACL):
Adam Roussel. 2023. Lexical Semantics with Vector Symbolic Architectures. In Proceedings of the Second Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2023), pages 53–61, Tórshavn, the Faroe Islands. Association for Computational Linguistics.
Cite (Informal):
Lexical Semantics with Vector Symbolic Architectures (Roussel, RESOURCEFUL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.resourceful-1.8.pdf