Unsupervised Statistical Learning of Context-free Grammar

Olgierd Unold, Mateusz Gabor, Wojciech Wieczorek

Abstract

In this paper, we address the problem of inducing (weighted) context-free grammar (WCFG) on data given. The induction is performed by using a new model of grammatical inference, i.e., weighted Grammar-based Classifier System (wGCS). wGCS derives from learning classifier systems and searches grammar structure using a genetic algorithm and covering. Weights of rules are estimated by using a novelty Inside-Outside Contrastive Estimation algorithm. The proposed method employs direct negative evidence and learns WCFG both form positive and negative samples. Results of experiments on three synthetic context-free languages show that wGCS is competitive with other statistical-based method for unsupervised CFG learning.

Download


Paper Citation


in Harvard Style

Unold O., Gabor M. and Wieczorek W. (2020). Unsupervised Statistical Learning of Context-free Grammar.In Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 1: NLPinAI, ISBN 978-989-758-395-7, pages 431-438. DOI: 10.5220/0009383604310438


in Bibtex Style

@conference{nlpinai20,
author={Olgierd Unold and Mateusz Gabor and Wojciech Wieczorek},
title={Unsupervised Statistical Learning of Context-free Grammar},
booktitle={Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 1: NLPinAI,},
year={2020},
pages={431-438},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009383604310438},
isbn={978-989-758-395-7},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 1: NLPinAI,
TI - Unsupervised Statistical Learning of Context-free Grammar
SN - 978-989-758-395-7
AU - Unold O.
AU - Gabor M.
AU - Wieczorek W.
PY - 2020
SP - 431
EP - 438
DO - 10.5220/0009383604310438