A Canonical Semi-Deterministic Transducer
Machine Learning
2016-10-12 v4
Abstract
We prove the existence of a canonical form for semi-deterministic transducers with incomparable sets of output strings. Based on this, we develop an algorithm which learns semi-deterministic transducers given access to translation queries. We also prove that there is no learning algorithm for semi-deterministic transducers that uses only domain knowledge.
Keywords
Cite
@article{arxiv.1405.2476,
title = {A Canonical Semi-Deterministic Transducer},
author = {Achilles Beros and Colin de la Higuera},
journal= {arXiv preprint arXiv:1405.2476},
year = {2016}
}
Comments
A shorter version has been published in the proceedings of ICGI 2014. This version will appear in an issue of Fundamenta Informaticae