Learning tone sandhis in Structural Optimality

Izabel Ilie, Andrew Lamont, Brandon Prickett


Abstract
This paper examines the learnability of different types of tone sandhi in Structural Optimality, a constraint-based framework that posits hierarchical scales and defines constraints over the scales. Approached as a hidden structure problem, we show that Expectation Driven Parameter Learning can acquire these grammars, but that their properties can make learning difficult.
Anthology ID:
2026.scil-main.30
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:
329–337
Language:
URL:
https://preview.aclanthology.org/ingest-acl-workshops/2026.scil-main.30/
DOI:
Bibkey:
Cite (ACL):
Izabel Ilie, Andrew Lamont, and Brandon Prickett. 2026. Learning tone sandhis in Structural Optimality. In Proceedings of the Society for Computation in Linguistics 2026, pages 329–337, San Diego, CA. Association for Computational Linguistics.
Cite (Informal):
Learning tone sandhis in Structural Optimality (Ilie et al., SCiL 2026)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-acl-workshops/2026.scil-main.30.pdf