@inproceedings{ma-huang-2006-uniform,
title = "Uniform and Effective Tagging of a Heterogeneous Giga-word Corpus",
author = "Ma, Wei-Yun and
Huang, Chu-Ren",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Gangemi, Aldo and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Tapias, Daniel",
booktitle = "Proceedings of the Fifth International Conference on Language Resources and Evaluation ({LREC}{'}06)",
month = may,
year = "2006",
address = "Genoa, Italy",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2006/pdf/294_pdf.pdf",
abstract = "Tagging as the most crucial annotation of language resources can still be challenging when the corpus size is big and when the corpus data is not homogeneous. The Chinese Gigaword Corpus is confounded by both challenges. The corpus containsroughly 1.12 billion Chinese characters from two heterogeneous sources: respective news in Taiwan and in Mainland China. In other words, in addition to its size, the data also contains two variants of Chinese that are known to exhibit substantial linguistic differences. We utilize Chinese Sketch Engine as the corpus query tool, by which grammar behaviours of the two heterogeneous resources could be captured and displayed in a unified web interface. In this paper, we report our answer to the two challenges to effectively tag this large-scale corpus. The evaluation result shows our mechanism of tagging maintains high annotation quality.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ma-huang-2006-uniform">
<titleInfo>
<title>Uniform and Effective Tagging of a Heterogeneous Giga-word Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wei-Yun</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2006-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)</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">Aldo</namePart>
<namePart type="family">Gangemi</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">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">Genoa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Tagging as the most crucial annotation of language resources can still be challenging when the corpus size is big and when the corpus data is not homogeneous. The Chinese Gigaword Corpus is confounded by both challenges. The corpus containsroughly 1.12 billion Chinese characters from two heterogeneous sources: respective news in Taiwan and in Mainland China. In other words, in addition to its size, the data also contains two variants of Chinese that are known to exhibit substantial linguistic differences. We utilize Chinese Sketch Engine as the corpus query tool, by which grammar behaviours of the two heterogeneous resources could be captured and displayed in a unified web interface. In this paper, we report our answer to the two challenges to effectively tag this large-scale corpus. The evaluation result shows our mechanism of tagging maintains high annotation quality.</abstract>
<identifier type="citekey">ma-huang-2006-uniform</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/294_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Uniform and Effective Tagging of a Heterogeneous Giga-word Corpus
%A Ma, Wei-Yun
%A Huang, Chu-Ren
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Gangemi, Aldo
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Tapias, Daniel
%S Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)
%D 2006
%8 May
%I European Language Resources Association (ELRA)
%C Genoa, Italy
%F ma-huang-2006-uniform
%X Tagging as the most crucial annotation of language resources can still be challenging when the corpus size is big and when the corpus data is not homogeneous. The Chinese Gigaword Corpus is confounded by both challenges. The corpus containsroughly 1.12 billion Chinese characters from two heterogeneous sources: respective news in Taiwan and in Mainland China. In other words, in addition to its size, the data also contains two variants of Chinese that are known to exhibit substantial linguistic differences. We utilize Chinese Sketch Engine as the corpus query tool, by which grammar behaviours of the two heterogeneous resources could be captured and displayed in a unified web interface. In this paper, we report our answer to the two challenges to effectively tag this large-scale corpus. The evaluation result shows our mechanism of tagging maintains high annotation quality.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/294_pdf.pdf
Markdown (Informal)
[Uniform and Effective Tagging of a Heterogeneous Giga-word Corpus](http://www.lrec-conf.org/proceedings/lrec2006/pdf/294_pdf.pdf) (Ma & Huang, LREC 2006)
ACL