In this paper, we introduce the concept of Multiclass for language modeling and we compare it to the Polyclass model. The originality of the Multiclass is its capability to parse a string of class/tags into variable length independent sequences. A few experimental tests were carried out on a class corpus extracted from the French "Le Monde" word corpus labeled automatically. This corpus contains a set of 43 million of words. In our experiments, Multiclass outperform first-order Polyclass but are slightly outperformed by second-order Polyclass.
Cite as: Zitouni, I., Smaili, K., Haton, J.-P., Deligne, S., Bimbot, F. (1998) A comparative study between polyclass and multiclass language models. Proc. 5th International Conference on Spoken Language Processing (ICSLP 1998), paper 0498, doi: 10.21437/ICSLP.1998-622
@inproceedings{zitouni98_icslp,
author={Imed Zitouni and Kamel Smaili and Jean-Paul Haton and Sabine Deligne and Frédéric Bimbot},
title={{A comparative study between polyclass and multiclass language models}},
year=1998,
booktitle={Proc. 5th International Conference on Spoken Language Processing (ICSLP 1998)},
pages={paper 0498},
doi={10.21437/ICSLP.1998-622}
}