TTR at the SPA: Relating type-theoretical semantics to neural semantic pointers

Staffan Larsson, Robin Cooper, Jonathan Ginzburg, Andy Luecking


Abstract
This paper considers how the kind of formal semantic objects used in TTR (a theory of types with records, Cooper 2013) might be related to the vector representations used in Eliasmith (2013). An advantage of doing this is that it would immediately give us a neural representation for TTR objects as Eliasmith relates vectors to neural activity in his semantic pointer architecture (SPA). This would be an alternative using convolution to the suggestions made by Cooper (2019) based on the phasing of neural activity. The project seems potentially hopeful since all complex TTR objects are constructed from labelled sets (essentially sets of ordered pairs consisting of labels and values) which might be seen as corresponding to the representation of structured objects which Eliasmith achieves using superposition and circular convolution.
Anthology ID:
2023.naloma-1.5
Volume:
Proceedings of the 4th Natural Logic Meets Machine Learning Workshop
Month:
June
Year:
2023
Address:
Nancy, France
Editors:
Stergios Chatzikyriakidis, Valeria de Paiva
Venues:
NALOMA | WS
SIG:
SIGSEM
Publisher:
Association for Computational Linguistics
Note:
Pages:
41–50
Language:
URL:
https://aclanthology.org/2023.naloma-1.5
DOI:
Bibkey:
Cite (ACL):
Staffan Larsson, Robin Cooper, Jonathan Ginzburg, and Andy Luecking. 2023. TTR at the SPA: Relating type-theoretical semantics to neural semantic pointers. In Proceedings of the 4th Natural Logic Meets Machine Learning Workshop, pages 41–50, Nancy, France. Association for Computational Linguistics.
Cite (Informal):
TTR at the SPA: Relating type-theoretical semantics to neural semantic pointers (Larsson et al., NALOMA-WS 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.naloma-1.5.pdf