@inproceedings{smaili-etal-2006-linguistic,
title = "Linguistic features modeling based on Partial New Cache",
author = {Sma{\"\i}li, Kamel and
Lavecchia, Caroline and
Haton, Jean-Paul},
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/721_pdf.pdf",
abstract = "The agreement in gender and number is a critical problem in statistical language modeling. One of the main problems in the speech recognition of French language is the presence of misrecognized words due to the bad agreement (in gender and number) between words. Statistical language models do not treat this phenomenon directly. This paper focuses on how to handle the issue of agreements. We introduce an original model called Features-Cache (FC) to estimate the gender and the number of the word to predict. It is a dynamic variable-length Features-Cache for which the size is determined in accordance to syntagm delimitors. This model does not need any syntactic parsing, it is used as any other statistical language model. Several models have been carried out and the best one achieves an improvement of more than 8 points in terms of perplexity.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="smaili-etal-2006-linguistic">
<titleInfo>
<title>Linguistic features modeling based on Partial New Cache</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kamel</namePart>
<namePart type="family">Smaïli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Caroline</namePart>
<namePart type="family">Lavecchia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jean-Paul</namePart>
<namePart type="family">Haton</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>The agreement in gender and number is a critical problem in statistical language modeling. One of the main problems in the speech recognition of French language is the presence of misrecognized words due to the bad agreement (in gender and number) between words. Statistical language models do not treat this phenomenon directly. This paper focuses on how to handle the issue of agreements. We introduce an original model called Features-Cache (FC) to estimate the gender and the number of the word to predict. It is a dynamic variable-length Features-Cache for which the size is determined in accordance to syntagm delimitors. This model does not need any syntactic parsing, it is used as any other statistical language model. Several models have been carried out and the best one achieves an improvement of more than 8 points in terms of perplexity.</abstract>
<identifier type="citekey">smaili-etal-2006-linguistic</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/721_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Linguistic features modeling based on Partial New Cache
%A Smaïli, Kamel
%A Lavecchia, Caroline
%A Haton, Jean-Paul
%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 smaili-etal-2006-linguistic
%X The agreement in gender and number is a critical problem in statistical language modeling. One of the main problems in the speech recognition of French language is the presence of misrecognized words due to the bad agreement (in gender and number) between words. Statistical language models do not treat this phenomenon directly. This paper focuses on how to handle the issue of agreements. We introduce an original model called Features-Cache (FC) to estimate the gender and the number of the word to predict. It is a dynamic variable-length Features-Cache for which the size is determined in accordance to syntagm delimitors. This model does not need any syntactic parsing, it is used as any other statistical language model. Several models have been carried out and the best one achieves an improvement of more than 8 points in terms of perplexity.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/721_pdf.pdf
Markdown (Informal)
[Linguistic features modeling based on Partial New Cache](http://www.lrec-conf.org/proceedings/lrec2006/pdf/721_pdf.pdf) (Smaïli et al., LREC 2006)
ACL
- Kamel Smaïli, Caroline Lavecchia, and Jean-Paul Haton. 2006. Linguistic features modeling based on Partial New Cache. In Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06), Genoa, Italy. European Language Resources Association (ELRA).