A Feature-Driven Tensor Semantics for Minimalist Grammars

John Paulson, Aniello De Santo, Jonathan Rawski


Abstract
This paper shows how tensor-based distributional semantics can be incorporated into Minimalist Grammars (MGs), leveraging the tensor-based MG representations of beim Graben and Gerth (2012). We embed the Minimalist feature calculus with a tensor algebra and give a joint tensor-based representation where compositional semantics is guided by the minimalist syntax. By bridging syntactic and semantic operation in tensor spaces, we aim to contribute to the broader enterprise of neurosymbolic approaches to linguistic cognition.
Anthology ID:
2026.scil-main.20
Volume:
Proceedings of the Society for Computation in Linguistics 2026
Month:
July
Year:
2026
Address:
San Diego, CA
Editors:
Rob Voigt, Alex Warstadt, Naomi Feldman, Tal Linzen
Venues:
SCiL | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
219–229
Language:
URL:
https://preview.aclanthology.org/ingest-acl-workshops/2026.scil-main.20/
DOI:
Bibkey:
Cite (ACL):
John Paulson, Aniello De Santo, and Jonathan Rawski. 2026. A Feature-Driven Tensor Semantics for Minimalist Grammars. In Proceedings of the Society for Computation in Linguistics 2026, pages 219–229, San Diego, CA. Association for Computational Linguistics.
Cite (Informal):
A Feature-Driven Tensor Semantics for Minimalist Grammars (Paulson et al., SCiL 2026)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-acl-workshops/2026.scil-main.20.pdf