@inproceedings{wandmacher-antoine-2006-training,
title = "Training Language Models without Appropriate Language Resources: Experiments with an {AAC} System for Disabled People",
author = "Wandmacher, Tonio and
Antoine, Jean-Yves",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Gangemi, Aldo and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Tapias, Daniel",
booktitle = "Proceedings of the Fifth International Conference on Language Resources and Evaluation ({LREC}{'}06)",
month = may,
year = "2006",
address = "Genoa, Italy",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2006/pdf/113_pdf.pdf",
abstract = "Statistical Language Models (LM) are highly dependent on their training resources. This makes it not only difficult to interpret evaluation results, it also has a deteriorating effect on the use of an LM-based application. This question has already been studied by others. Considering a specific domain (text prediction in a communication aid for handicapped people) we want to address the problem from a different point of view: the influence of the language register. Considering corpora from five different registers, we want to discuss three methods to adapt a language model to its actual language resource ultimately reducing the effect of training dependency: (a) A simple cache model augmenting the probability of the n last inserted words; (b) a user dictionary, keeping every unseen word; and (c) a combined LM interpolating a base model with a dynamically updated user model. Our evaluation is based on the results obtained from a text prediction system working on a trigram LM.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wandmacher-antoine-2006-training">
<titleInfo>
<title>Training Language Models without Appropriate Language Resources: Experiments with an AAC System for Disabled People</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tonio</namePart>
<namePart type="family">Wandmacher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jean-Yves</namePart>
<namePart type="family">Antoine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2006-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aldo</namePart>
<namePart type="family">Gangemi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Genoa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Statistical Language Models (LM) are highly dependent on their training resources. This makes it not only difficult to interpret evaluation results, it also has a deteriorating effect on the use of an LM-based application. This question has already been studied by others. Considering a specific domain (text prediction in a communication aid for handicapped people) we want to address the problem from a different point of view: the influence of the language register. Considering corpora from five different registers, we want to discuss three methods to adapt a language model to its actual language resource ultimately reducing the effect of training dependency: (a) A simple cache model augmenting the probability of the n last inserted words; (b) a user dictionary, keeping every unseen word; and (c) a combined LM interpolating a base model with a dynamically updated user model. Our evaluation is based on the results obtained from a text prediction system working on a trigram LM.</abstract>
<identifier type="citekey">wandmacher-antoine-2006-training</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/113_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Training Language Models without Appropriate Language Resources: Experiments with an AAC System for Disabled People
%A Wandmacher, Tonio
%A Antoine, Jean-Yves
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Gangemi, Aldo
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Tapias, Daniel
%S Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)
%D 2006
%8 May
%I European Language Resources Association (ELRA)
%C Genoa, Italy
%F wandmacher-antoine-2006-training
%X Statistical Language Models (LM) are highly dependent on their training resources. This makes it not only difficult to interpret evaluation results, it also has a deteriorating effect on the use of an LM-based application. This question has already been studied by others. Considering a specific domain (text prediction in a communication aid for handicapped people) we want to address the problem from a different point of view: the influence of the language register. Considering corpora from five different registers, we want to discuss three methods to adapt a language model to its actual language resource ultimately reducing the effect of training dependency: (a) A simple cache model augmenting the probability of the n last inserted words; (b) a user dictionary, keeping every unseen word; and (c) a combined LM interpolating a base model with a dynamically updated user model. Our evaluation is based on the results obtained from a text prediction system working on a trigram LM.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/113_pdf.pdf
Markdown (Informal)
[Training Language Models without Appropriate Language Resources: Experiments with an AAC System for Disabled People](http://www.lrec-conf.org/proceedings/lrec2006/pdf/113_pdf.pdf) (Wandmacher & Antoine, LREC 2006)
ACL