@inproceedings{zhao-etal-2010-large,
title = "How Large a Corpus Do We Need: Statistical Method Versus Rule-based Method",
author = "Zhao, Hai and
Song, Yan and
Kit, Chunyu",
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/199_Paper.pdf",
abstract = "We investigate the impact of input data scale in corpus-based learning using a study style of Zipfs law. In our research, Chinese word segmentation is chosen as the study case and a series of experiments are specially conducted for it, in which two types of segmentation techniques, statistical learning and rule-based methods, are examined. The empirical results show that a linear performance improvement in statistical learning requires an exponential increasing of training corpus size at least. As for the rule-based method, an approximate negative inverse relationship between the performance and the size of the input lexicon can be observed.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-etal-2010-large">
<titleInfo>
<title>How Large a Corpus Do We Need: Statistical Method Versus Rule-based Method</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hai</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chunyu</namePart>
<namePart type="family">Kit</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>We investigate the impact of input data scale in corpus-based learning using a study style of Zipfs law. In our research, Chinese word segmentation is chosen as the study case and a series of experiments are specially conducted for it, in which two types of segmentation techniques, statistical learning and rule-based methods, are examined. The empirical results show that a linear performance improvement in statistical learning requires an exponential increasing of training corpus size at least. As for the rule-based method, an approximate negative inverse relationship between the performance and the size of the input lexicon can be observed.</abstract>
<identifier type="citekey">zhao-etal-2010-large</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/199_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How Large a Corpus Do We Need: Statistical Method Versus Rule-based Method
%A Zhao, Hai
%A Song, Yan
%A Kit, Chunyu
%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 zhao-etal-2010-large
%X We investigate the impact of input data scale in corpus-based learning using a study style of Zipfs law. In our research, Chinese word segmentation is chosen as the study case and a series of experiments are specially conducted for it, in which two types of segmentation techniques, statistical learning and rule-based methods, are examined. The empirical results show that a linear performance improvement in statistical learning requires an exponential increasing of training corpus size at least. As for the rule-based method, an approximate negative inverse relationship between the performance and the size of the input lexicon can be observed.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/199_Paper.pdf
Markdown (Informal)
[How Large a Corpus Do We Need: Statistical Method Versus Rule-based Method](http://www.lrec-conf.org/proceedings/lrec2010/pdf/199_Paper.pdf) (Zhao et al., LREC 2010)
ACL