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