Learning Probabilistic Subsequential Transducers from Positive Data

Hasan Ibne Akram, Colin de la Higuera

2013

Abstract

In this paper we present a novel algorithm for learning probabilistic subsequential transducers from a randomly drawn sample. We formalize the properties of the training data that are sufficient conditions for the learning algorithm to infer the correct machine. Finally, we report experimental evidences to backup the correctness of our proposed algorithm.

Paper Citation

in Harvard Style

Ibne Akram H. and de la Higuera C. (2013). Learning Probabilistic Subsequential Transducers from Positive Data . In Proceedings of the 5th International Conference on Agents and Artificial Intelligence - Volume 1: LAFLang, (ICAART 2013) ISBN 978-989-8565-38-9, pages 479-486. DOI: 10.5220/0004359904790486

in Bibtex Style

@conference{laflang13,
author={Hasan Ibne Akram and Colin de la Higuera},
title={Learning Probabilistic Subsequential Transducers from Positive Data},
booktitle={Proceedings of the 5th International Conference on Agents and Artificial Intelligence - Volume 1: LAFLang, (ICAART 2013)},
year={2013},
pages={479-486},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004359904790486},
isbn={978-989-8565-38-9},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 5th International Conference on Agents and Artificial Intelligence - Volume 1: LAFLang, (ICAART 2013)
TI - Learning Probabilistic Subsequential Transducers from Positive Data
SN - 978-989-8565-38-9
AU - Ibne Akram H.
AU - de la Higuera C.
PY - 2013
SP - 479
EP - 486
DO - 10.5220/0004359904790486