@inproceedings{guthrie-etal-2010-efficient,
title = "Efficient Minimal Perfect Hash Language Models",
author = "Guthrie, David and
Hepple, Mark and
Liu, Wei",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/860_Paper.pdf",
abstract = "The availability of large collections of text have made it possible to build language models that incorporate counts of billions of n-grams. This paper proposes two new methods of efficiently storing large language models that allow O(1) random access and use significantly less space than all known approaches. We introduce two novel data structures that take advantage of the distribution of n-grams in corpora and make use of various numbers of minimal perfect hashes to compactly store language models containing full frequency counts of billions of n-grams using 2.5 Bytes per n-gram and language models of quantized probabilities using 2.26 Bytes per n-gram. These methods allow language processing applications to take advantage of much larger language models than previously was possible using the same hardware and we additionally describe how they can be used in a distributed environment to store even larger models. We show that our approaches are simple to implement and can easily be combined with pruning and quantization to achieve additional reductions in the size of the language model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guthrie-etal-2010-efficient">
<titleInfo>
<title>Efficient Minimal Perfect Hash Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Guthrie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Hepple</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">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">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</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">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The availability of large collections of text have made it possible to build language models that incorporate counts of billions of n-grams. This paper proposes two new methods of efficiently storing large language models that allow O(1) random access and use significantly less space than all known approaches. We introduce two novel data structures that take advantage of the distribution of n-grams in corpora and make use of various numbers of minimal perfect hashes to compactly store language models containing full frequency counts of billions of n-grams using 2.5 Bytes per n-gram and language models of quantized probabilities using 2.26 Bytes per n-gram. These methods allow language processing applications to take advantage of much larger language models than previously was possible using the same hardware and we additionally describe how they can be used in a distributed environment to store even larger models. We show that our approaches are simple to implement and can easily be combined with pruning and quantization to achieve additional reductions in the size of the language model.</abstract>
<identifier type="citekey">guthrie-etal-2010-efficient</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/860_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Efficient Minimal Perfect Hash Language Models
%A Guthrie, David
%A Hepple, Mark
%A Liu, Wei
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F guthrie-etal-2010-efficient
%X The availability of large collections of text have made it possible to build language models that incorporate counts of billions of n-grams. This paper proposes two new methods of efficiently storing large language models that allow O(1) random access and use significantly less space than all known approaches. We introduce two novel data structures that take advantage of the distribution of n-grams in corpora and make use of various numbers of minimal perfect hashes to compactly store language models containing full frequency counts of billions of n-grams using 2.5 Bytes per n-gram and language models of quantized probabilities using 2.26 Bytes per n-gram. These methods allow language processing applications to take advantage of much larger language models than previously was possible using the same hardware and we additionally describe how they can be used in a distributed environment to store even larger models. We show that our approaches are simple to implement and can easily be combined with pruning and quantization to achieve additional reductions in the size of the language model.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/860_Paper.pdf
Markdown (Informal)
[Efficient Minimal Perfect Hash Language Models](http://www.lrec-conf.org/proceedings/lrec2010/pdf/860_Paper.pdf) (Guthrie et al., LREC 2010)
ACL
- David Guthrie, Mark Hepple, and Wei Liu. 2010. Efficient Minimal Perfect Hash Language Models. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).