Simple Variable Length N-grams for Probabilistic Automata Learning

Fabio N. Kepler, Sergio L. S. Mergen, Cleo Z. Billa
Proceedings of the Eleventh International Conference on Grammatical Inference, PMLR 21:254-258, 2012.

Abstract

This paper describes an approach used in the 2012 Probabilistic Automata Learning Competition. The main goal of the competition was to obtain insights about which techniques and approaches work best for sequence learning based on different kinds of automata generating machines. This paper proposes the usage of n-gram models with variable length. Experiments show that, using the test sets provided by the competition, the variable-length approach works better than fixed 3-grams.

Cite this Paper

BibTeX
@InProceedings{pmlr-v21-kepler12a, title = {Simple Variable Length N-grams for Probabilistic Automata Learning}, author = {Kepler, Fabio N. and Mergen, Sergio L. S. and Billa, Cleo Z.}, booktitle = {Proceedings of the Eleventh International Conference on Grammatical Inference}, pages = {254--258}, year = {2012}, editor = {Heinz, Jeffrey and Higuera, Colin and Oates, Tim}, volume = {21}, series = {Proceedings of Machine Learning Research}, address = {University of Maryland, College Park, MD, USA}, month = {05--08 Sep}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v21/kepler12a/kepler12a.pdf}, url = {https://proceedings.mlr.press/v21/kepler12a.html}, abstract = {This paper describes an approach used in the 2012 Probabilistic Automata Learning Competition. The main goal of the competition was to obtain insights about which techniques and approaches work best for sequence learning based on different kinds of automata generating machines. This paper proposes the usage of n-gram models with variable length. Experiments show that, using the test sets provided by the competition, the variable-length approach works better than fixed 3-grams.} }
Endnote
%0 Conference Paper %T Simple Variable Length N-grams for Probabilistic Automata Learning %A Fabio N. Kepler %A Sergio L. S. Mergen %A Cleo Z. Billa %B Proceedings of the Eleventh International Conference on Grammatical Inference %C Proceedings of Machine Learning Research %D 2012 %E Jeffrey Heinz %E Colin Higuera %E Tim Oates %F pmlr-v21-kepler12a %I PMLR %P 254--258 %U https://proceedings.mlr.press/v21/kepler12a.html %V 21 %X This paper describes an approach used in the 2012 Probabilistic Automata Learning Competition. The main goal of the competition was to obtain insights about which techniques and approaches work best for sequence learning based on different kinds of automata generating machines. This paper proposes the usage of n-gram models with variable length. Experiments show that, using the test sets provided by the competition, the variable-length approach works better than fixed 3-grams.
RIS
TY - CPAPER TI - Simple Variable Length N-grams for Probabilistic Automata Learning AU - Fabio N. Kepler AU - Sergio L. S. Mergen AU - Cleo Z. Billa BT - Proceedings of the Eleventh International Conference on Grammatical Inference DA - 2012/08/16 ED - Jeffrey Heinz ED - Colin Higuera ED - Tim Oates ID - pmlr-v21-kepler12a PB - PMLR DP - Proceedings of Machine Learning Research VL - 21 SP - 254 EP - 258 L1 - http://proceedings.mlr.press/v21/kepler12a/kepler12a.pdf UR - https://proceedings.mlr.press/v21/kepler12a.html AB - This paper describes an approach used in the 2012 Probabilistic Automata Learning Competition. The main goal of the competition was to obtain insights about which techniques and approaches work best for sequence learning based on different kinds of automata generating machines. This paper proposes the usage of n-gram models with variable length. Experiments show that, using the test sets provided by the competition, the variable-length approach works better than fixed 3-grams. ER -
APA
Kepler, F.N., Mergen, S.L.S. & Billa, C.Z.. (2012). Simple Variable Length N-grams for Probabilistic Automata Learning. Proceedings of the Eleventh International Conference on Grammatical Inference, in Proceedings of Machine Learning Research 21:254-258 Available from https://proceedings.mlr.press/v21/kepler12a.html.

Related Material