@inproceedings{kennington-etal-2012-suffix,
title = "Suffix Trees as Language Models",
author = "Kennington, Casey Redd and
Kay, Martin and
Friedrich, Annemarie",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/649_Paper.pdf",
pages = "446--453",
abstract = "Suffix trees are data structures that can be used to index a corpus. In this paper, we explore how some properties of suffix trees naturally provide the functionality of an n-gram language model with variable n. We explain these properties of suffix trees, which we leverage for our Suffix Tree Language Model (STLM) implementation and explain how a suffix tree implicitly contains the data needed for n-gram language modeling. We also discuss the kinds of smoothing techniques appropriate to such a model. We then show that our suffix-tree language model implementation is competitive when compared to the state-of-the-art language model SRILM (Stolke, 2002) in statistical machine translation experiments.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kennington-etal-2012-suffix">
<titleInfo>
<title>Suffix Trees as Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Casey</namePart>
<namePart type="given">Redd</namePart>
<namePart type="family">Kennington</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Kay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annemarie</namePart>
<namePart type="family">Friedrich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Suffix trees are data structures that can be used to index a corpus. In this paper, we explore how some properties of suffix trees naturally provide the functionality of an n-gram language model with variable n. We explain these properties of suffix trees, which we leverage for our Suffix Tree Language Model (STLM) implementation and explain how a suffix tree implicitly contains the data needed for n-gram language modeling. We also discuss the kinds of smoothing techniques appropriate to such a model. We then show that our suffix-tree language model implementation is competitive when compared to the state-of-the-art language model SRILM (Stolke, 2002) in statistical machine translation experiments.</abstract>
<identifier type="citekey">kennington-etal-2012-suffix</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/649_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>446</start>
<end>453</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Suffix Trees as Language Models
%A Kennington, Casey Redd
%A Kay, Martin
%A Friedrich, Annemarie
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F kennington-etal-2012-suffix
%X Suffix trees are data structures that can be used to index a corpus. In this paper, we explore how some properties of suffix trees naturally provide the functionality of an n-gram language model with variable n. We explain these properties of suffix trees, which we leverage for our Suffix Tree Language Model (STLM) implementation and explain how a suffix tree implicitly contains the data needed for n-gram language modeling. We also discuss the kinds of smoothing techniques appropriate to such a model. We then show that our suffix-tree language model implementation is competitive when compared to the state-of-the-art language model SRILM (Stolke, 2002) in statistical machine translation experiments.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/649_Paper.pdf
%P 446-453
Markdown (Informal)
[Suffix Trees as Language Models](http://www.lrec-conf.org/proceedings/lrec2012/pdf/649_Paper.pdf) (Kennington et al., LREC 2012)
ACL
- Casey Redd Kennington, Martin Kay, and Annemarie Friedrich. 2012. Suffix Trees as Language Models. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 446–453, Istanbul, Turkey. European Language Resources Association (ELRA).