@inproceedings{buck-etal-2014-n,
title = "{N}-gram Counts and Language Models from the {C}ommon {C}rawl",
author = "Buck, Christian and
Heafield, Kenneth and
van Ooyen, Bas",
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/1097_Paper.pdf",
pages = "3579--3584",
abstract = "We contribute 5-gram counts and language models trained on the Common Crawl corpus, a collection over 9 billion web pages. This release improves upon the Google n-gram counts in two key ways: the inclusion of low-count entries and deduplication to reduce boilerplate. By preserving singletons, we were able to use Kneser-Ney smoothing to build large language models. This paper describes how the corpus was processed with emphasis on the problems that arise in working with data at this scale. Our unpruned Kneser-Ney English 5-gram language model, built on 975 billion deduplicated tokens, contains over 500 billion unique n-grams. We show gains of 0.5-1.4 BLEU by using large language models to translate into various languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="buck-etal-2014-n">
<titleInfo>
<title>N-gram Counts and Language Models from the Common Crawl</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Buck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kenneth</namePart>
<namePart type="family">Heafield</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bas</namePart>
<namePart type="family">van Ooyen</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>We contribute 5-gram counts and language models trained on the Common Crawl corpus, a collection over 9 billion web pages. This release improves upon the Google n-gram counts in two key ways: the inclusion of low-count entries and deduplication to reduce boilerplate. By preserving singletons, we were able to use Kneser-Ney smoothing to build large language models. This paper describes how the corpus was processed with emphasis on the problems that arise in working with data at this scale. Our unpruned Kneser-Ney English 5-gram language model, built on 975 billion deduplicated tokens, contains over 500 billion unique n-grams. We show gains of 0.5-1.4 BLEU by using large language models to translate into various languages.</abstract>
<identifier type="citekey">buck-etal-2014-n</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/1097_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>3579</start>
<end>3584</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T N-gram Counts and Language Models from the Common Crawl
%A Buck, Christian
%A Heafield, Kenneth
%A van Ooyen, Bas
%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 buck-etal-2014-n
%X We contribute 5-gram counts and language models trained on the Common Crawl corpus, a collection over 9 billion web pages. This release improves upon the Google n-gram counts in two key ways: the inclusion of low-count entries and deduplication to reduce boilerplate. By preserving singletons, we were able to use Kneser-Ney smoothing to build large language models. This paper describes how the corpus was processed with emphasis on the problems that arise in working with data at this scale. Our unpruned Kneser-Ney English 5-gram language model, built on 975 billion deduplicated tokens, contains over 500 billion unique n-grams. We show gains of 0.5-1.4 BLEU by using large language models to translate into various languages.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/1097_Paper.pdf
%P 3579-3584
Markdown (Informal)
[N-gram Counts and Language Models from the Common Crawl](http://www.lrec-conf.org/proceedings/lrec2014/pdf/1097_Paper.pdf) (Buck et al., LREC 2014)
ACL
- Christian Buck, Kenneth Heafield, and Bas van Ooyen. 2014. N-gram Counts and Language Models from the Common Crawl. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 3579–3584, Reykjavik, Iceland. European Language Resources Association (ELRA).