@inproceedings{pelemans-etal-2016-scale,
title = "{SCALE}: A Scalable Language Engineering Toolkit",
author = "Pelemans, Joris and
Verwimp, Lyan and
Demuynck, Kris and
Van hamme, Hugo and
Wambacq, Patrick",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1612",
pages = "3868--3871",
abstract = "In this paper we present SCALE, a new Python toolkit that contains two extensions to n-gram language models. The first extension is a novel technique to model compound words called Semantic Head Mapping (SHM). The second extension, Bag-of-Words Language Modeling (BagLM), bundles popular models such as Latent Semantic Analysis and Continuous Skip-grams. Both extensions scale to large data and allow the integration into first-pass ASR decoding. The toolkit is open source, includes working examples and can be found on \url{http://github.com/jorispelemans/scale}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pelemans-etal-2016-scale">
<titleInfo>
<title>SCALE: A Scalable Language Engineering Toolkit</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joris</namePart>
<namePart type="family">Pelemans</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lyan</namePart>
<namePart type="family">Verwimp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kris</namePart>
<namePart type="family">Demuynck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hugo</namePart>
<namePart type="family">Van hamme</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Wambacq</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</namePart>
<namePart type="family">Mazo</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">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper we present SCALE, a new Python toolkit that contains two extensions to n-gram language models. The first extension is a novel technique to model compound words called Semantic Head Mapping (SHM). The second extension, Bag-of-Words Language Modeling (BagLM), bundles popular models such as Latent Semantic Analysis and Continuous Skip-grams. Both extensions scale to large data and allow the integration into first-pass ASR decoding. The toolkit is open source, includes working examples and can be found on http://github.com/jorispelemans/scale.</abstract>
<identifier type="citekey">pelemans-etal-2016-scale</identifier>
<location>
<url>https://aclanthology.org/L16-1612</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>3868</start>
<end>3871</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SCALE: A Scalable Language Engineering Toolkit
%A Pelemans, Joris
%A Verwimp, Lyan
%A Demuynck, Kris
%A Van hamme, Hugo
%A Wambacq, Patrick
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F pelemans-etal-2016-scale
%X In this paper we present SCALE, a new Python toolkit that contains two extensions to n-gram language models. The first extension is a novel technique to model compound words called Semantic Head Mapping (SHM). The second extension, Bag-of-Words Language Modeling (BagLM), bundles popular models such as Latent Semantic Analysis and Continuous Skip-grams. Both extensions scale to large data and allow the integration into first-pass ASR decoding. The toolkit is open source, includes working examples and can be found on http://github.com/jorispelemans/scale.
%U https://aclanthology.org/L16-1612
%P 3868-3871
Markdown (Informal)
[SCALE: A Scalable Language Engineering Toolkit](https://aclanthology.org/L16-1612) (Pelemans et al., LREC 2016)
ACL
- Joris Pelemans, Lyan Verwimp, Kris Demuynck, Hugo Van hamme, and Patrick Wambacq. 2016. SCALE: A Scalable Language Engineering Toolkit. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 3868–3871, Portorož, Slovenia. European Language Resources Association (ELRA).