Rating-based property axes: Agentivity and split intransitivity

Eva Neu, Brian Dillon, Katrin Erk


Abstract
Many gradable properties have been found to be encoded as axes in embedding space. Most commonly, property axes are computed using seed words, but recent work has noted limitations to seed-based axes. Here, we present a novel methodology for computing property axes that is based on human ratings and does not require seeds. We apply this methodology to a particular problem at the syntax-semantics interface: which semantic properties of intransitive verbs affect their likelihood to occur in one of two syntactic structures, unergative and unaccusative. Comparing property axes that encode different semantic dimensions of the concept of agentivity, we find that properties like movement and being alive are a better predictor of the syntactic behavior of intransitives than goal-directedness or intentionality. We discuss the potential of rating-based axes for future work in semantics and at the syntax-semantics interface.
Anthology ID:
2026.scil-main.25
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:
280–290
Language:
URL:
https://preview.aclanthology.org/ingest-acl-workshops/2026.scil-main.25/
DOI:
Bibkey:
Cite (ACL):
Eva Neu, Brian Dillon, and Katrin Erk. 2026. Rating-based property axes: Agentivity and split intransitivity. In Proceedings of the Society for Computation in Linguistics 2026, pages 280–290, San Diego, CA. Association for Computational Linguistics.
Cite (Informal):
Rating-based property axes: Agentivity and split intransitivity (Neu et al., SCiL 2026)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-acl-workshops/2026.scil-main.25.pdf