@inproceedings{varjokallio-kurimo-2014-toolkit,
title = "A Toolkit for Efficient Learning of Lexical Units for Speech Recognition",
author = "Varjokallio, Matti and
Kurimo, Mikko",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/715_Paper.pdf",
pages = "3072--3075",
abstract = "String segmentation is an important and recurring problem in natural language processing and other domains. For morphologically rich languages, the amount of different word forms caused by morphological processes like agglutination, compounding and inflection, may be huge and causes problems for traditional word-based language modeling approach. Segmenting text into better modelable units is thus an important part of the modeling task. This work presents methods and a toolkit for learning segmentation models from text. The methods may be applied to lexical unit selection for speech recognition and also other segmentation tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="varjokallio-kurimo-2014-toolkit">
<titleInfo>
<title>A Toolkit for Efficient Learning of Lexical Units for Speech Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Matti</namePart>
<namePart type="family">Varjokallio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikko</namePart>
<namePart type="family">Kurimo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hrafn</namePart>
<namePart type="family">Loftsson</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">Asuncion</namePart>
<namePart type="family">Moreno</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">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>String segmentation is an important and recurring problem in natural language processing and other domains. For morphologically rich languages, the amount of different word forms caused by morphological processes like agglutination, compounding and inflection, may be huge and causes problems for traditional word-based language modeling approach. Segmenting text into better modelable units is thus an important part of the modeling task. This work presents methods and a toolkit for learning segmentation models from text. The methods may be applied to lexical unit selection for speech recognition and also other segmentation tasks.</abstract>
<identifier type="citekey">varjokallio-kurimo-2014-toolkit</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/715_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>3072</start>
<end>3075</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Toolkit for Efficient Learning of Lexical Units for Speech Recognition
%A Varjokallio, Matti
%A Kurimo, Mikko
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F varjokallio-kurimo-2014-toolkit
%X String segmentation is an important and recurring problem in natural language processing and other domains. For morphologically rich languages, the amount of different word forms caused by morphological processes like agglutination, compounding and inflection, may be huge and causes problems for traditional word-based language modeling approach. Segmenting text into better modelable units is thus an important part of the modeling task. This work presents methods and a toolkit for learning segmentation models from text. The methods may be applied to lexical unit selection for speech recognition and also other segmentation tasks.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/715_Paper.pdf
%P 3072-3075
Markdown (Informal)
[A Toolkit for Efficient Learning of Lexical Units for Speech Recognition](http://www.lrec-conf.org/proceedings/lrec2014/pdf/715_Paper.pdf) (Varjokallio & Kurimo, LREC 2014)
ACL