A COMPARATIVE STUDY BETWEEN POLYCLASS AND MULTICLASS LANGUAGE MODELS

I Zitouni 1 K Smaïli 2 S Deligne 3 F Bimbot 4
1 PAROLE - Analysis, perception and recognition of speech
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
2 SMarT - Statistical Machine Translation and Speech Modelization and Text
LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
4 PANAMA - Parcimonie et Nouveaux Algorithmes pour le Signal et la Modélisation Audio
Inria Rennes – Bretagne Atlantique , IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
Abstract : In this work, 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 classes/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.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [10 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01112912
Contributor : Kamel Smaïli <>
Submitted on : Tuesday, February 3, 2015 - 7:20:25 PM
Last modification on : Tuesday, December 18, 2018 - 4:38:02 PM
Document(s) archivé(s) le : Saturday, September 12, 2015 - 8:25:22 AM

File

ImedICSLP98.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01112912, version 1

Citation

I Zitouni, K Smaïli, S Deligne, F Bimbot. A COMPARATIVE STUDY BETWEEN POLYCLASS AND MULTICLASS LANGUAGE MODELS. Proceedings of the Fifth International Conference on Spoken Language Processing, 1998, Sydney, Australia. ⟨hal-01112912⟩

Share

Metrics

Record views

384

Files downloads

228