English

Equiprobable mappings in weighted constraint grammars

Computation and Language 2019-07-15 v1 Machine Learning

Abstract

We show that MaxEnt is so rich that it can distinguish between any two different mappings: there always exists a nonnegative weight vector which assigns them different MaxEnt probabilities. Stochastic HG instead does admit equiprobable mappings and we give a complete formal characterization of them. We compare these different predictions of the two frameworks on a test case of Finnish stress.

Cite

@article{arxiv.1907.05839,
  title  = {Equiprobable mappings in weighted constraint grammars},
  author = {Arto Anttila and Scott Borgeson and Giorgio Magri},
  journal= {arXiv preprint arXiv:1907.05839},
  year   = {2019}
}

Comments

10 pages; Proceedings of ACL Sigmorphon 2019

R2 v1 2026-06-23T10:19:47.443Z