Serveur d'exploration sur la recherche en informatique en Lorraine

Attention, ce site est en cours de développement !
Attention, site généré par des moyens informatiques à partir de corpus bruts.
Les informations ne sont donc pas validées.

A Comparative Study Between Polyclass and Multiclass Language Models

Identifieur interne : 00B931 ( Main/Merge ); précédent : 00B930; suivant : 00B932

A Comparative Study Between Polyclass and Multiclass Language Models

Auteurs : Imed Zitouni ; Kamel Smaïli ; Jean-Paul Haton [France] ; Sabine Deligne ; Frédéric Bimbot

Source :

RBID : CRIN:zitouni98a

English descriptors

Abstract

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.

Links toward previous steps (curation, corpus...)


Links to Exploration step

CRIN:zitouni98a

Le document en format XML

<record>
<TEI>
<teiHeader>
<fileDesc>
<titleStmt>
<title xml:lang="en" wicri:score="118">A Comparative Study Between Polyclass and Multiclass Language Models</title>
</titleStmt>
<publicationStmt>
<idno type="RBID">CRIN:zitouni98a</idno>
<date when="1998" year="1998">1998</date>
<idno type="wicri:Area/Crin/Corpus">002406</idno>
<idno type="wicri:Area/Crin/Curation">002406</idno>
<idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Curation">002406</idno>
<idno type="wicri:Area/Crin/Checkpoint">002458</idno>
<idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Checkpoint">002458</idno>
<idno type="wicri:Area/Main/Merge">00B931</idno>
</publicationStmt>
<sourceDesc>
<biblStruct>
<analytic>
<title xml:lang="en">A Comparative Study Between Polyclass and Multiclass Language Models</title>
<author>
<name sortKey="Zitouni, Imed" sort="Zitouni, Imed" uniqKey="Zitouni I" first="Imed" last="Zitouni">Imed Zitouni</name>
</author>
<author>
<name sortKey="Smaili, Kamel" sort="Smaili, Kamel" uniqKey="Smaili K" first="Kamel" last="Smaïli">Kamel Smaïli</name>
</author>
<author>
<name sortKey="Haton, Jean Paul" sort="Haton, Jean Paul" uniqKey="Haton J" first="Jean-Paul" last="Haton">Jean-Paul Haton</name>
<affiliation>
<country>France</country>
<placeName>
<settlement type="city">Nancy</settlement>
<region type="region" nuts="2">Grand Est</region>
<region type="region" nuts="2">Lorraine (région)</region>
</placeName>
<orgName type="laboratoire" n="5">Laboratoire lorrain de recherche en informatique et ses applications</orgName>
<orgName type="university">Université de Lorraine</orgName>
<orgName type="institution">Centre national de la recherche scientifique</orgName>
<orgName type="institution">Institut national de recherche en informatique et en automatique</orgName>
</affiliation>
</author>
<author>
<name sortKey="Deligne, Sabine" sort="Deligne, Sabine" uniqKey="Deligne S" first="Sabine" last="Deligne">Sabine Deligne</name>
</author>
<author>
<name sortKey="Bimbot, Frederic" sort="Bimbot, Frederic" uniqKey="Bimbot F" first="Frédéric" last="Bimbot">Frédéric Bimbot</name>
</author>
</analytic>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc>
<textClass>
<keywords scheme="KwdEn" xml:lang="en">
<term>language model</term>
<term>multiclass</term>
<term>n-class</term>
<term>n-gram</term>
<term>polyclass</term>
<term>speech recognition</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front>
<div type="abstract" xml:lang="en" wicri:score="945">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.</div>
</front>
</TEI>
</record>

Pour manipuler ce document sous Unix (Dilib)

EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Main/Merge
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 00B931 | SxmlIndent | more

Ou

HfdSelect -h $EXPLOR_AREA/Data/Main/Merge/biblio.hfd -nk 00B931 | SxmlIndent | more

Pour mettre un lien sur cette page dans le réseau Wicri

{{Explor lien
   |wiki=    Wicri/Lorraine
   |area=    InforLorV4
   |flux=    Main
   |étape=   Merge
   |type=    RBID
   |clé=     CRIN:zitouni98a
   |texte=   A Comparative Study Between Polyclass and Multiclass Language Models
}}

Wicri

This area was generated with Dilib version V0.6.33.
Data generation: Mon Jun 10 21:56:28 2019. Site generation: Fri Feb 25 15:29:27 2022