@inproceedings{xia-etal-2006-constructing,
title = "Constructing A {C}hinese Chat Language Corpus with A Two-Stage Incremental Annotation Approach",
author = "Xia, Yunqing and
Wong, Kam-Fai and
Li, Wenjie",
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/86_pdf.pdf",
abstract = "Chat language refers to the special human language widely used in the community of digital network chat. As chat language holds anomalous characteristics in forming words, phrases, and non-alphabetical characters, conventional natural language processing tools are ineffective to handle chat language text. Previous research shows that knowledge based methods perform less effectively in proc-essing unseen chat terms. This motivates us to construct a chat language corpus so that corpus-based techniques of chat language text processing can be developed and evaluated. However, creating the corpus merely by hand is difficult. One, this work is manpower consuming. Second, annotation inconsistency is serious. To minimize manpower and annotation inconsistency, a two-stage incre-mental annotation approach is proposed in this paper in constructing a chat language corpus. Experiments conducted in this paper show that the performance of corpus annotation can be improved greatly with this approach.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xia-etal-2006-constructing">
<titleInfo>
<title>Constructing A Chinese Chat Language Corpus with A Two-Stage Incremental Annotation Approach</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yunqing</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kam-Fai</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</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>Chat language refers to the special human language widely used in the community of digital network chat. As chat language holds anomalous characteristics in forming words, phrases, and non-alphabetical characters, conventional natural language processing tools are ineffective to handle chat language text. Previous research shows that knowledge based methods perform less effectively in proc-essing unseen chat terms. This motivates us to construct a chat language corpus so that corpus-based techniques of chat language text processing can be developed and evaluated. However, creating the corpus merely by hand is difficult. One, this work is manpower consuming. Second, annotation inconsistency is serious. To minimize manpower and annotation inconsistency, a two-stage incre-mental annotation approach is proposed in this paper in constructing a chat language corpus. Experiments conducted in this paper show that the performance of corpus annotation can be improved greatly with this approach.</abstract>
<identifier type="citekey">xia-etal-2006-constructing</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/86_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Constructing A Chinese Chat Language Corpus with A Two-Stage Incremental Annotation Approach
%A Xia, Yunqing
%A Wong, Kam-Fai
%A Li, Wenjie
%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 xia-etal-2006-constructing
%X Chat language refers to the special human language widely used in the community of digital network chat. As chat language holds anomalous characteristics in forming words, phrases, and non-alphabetical characters, conventional natural language processing tools are ineffective to handle chat language text. Previous research shows that knowledge based methods perform less effectively in proc-essing unseen chat terms. This motivates us to construct a chat language corpus so that corpus-based techniques of chat language text processing can be developed and evaluated. However, creating the corpus merely by hand is difficult. One, this work is manpower consuming. Second, annotation inconsistency is serious. To minimize manpower and annotation inconsistency, a two-stage incre-mental annotation approach is proposed in this paper in constructing a chat language corpus. Experiments conducted in this paper show that the performance of corpus annotation can be improved greatly with this approach.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/86_pdf.pdf
Markdown (Informal)
[Constructing A Chinese Chat Language Corpus with A Two-Stage Incremental Annotation Approach](http://www.lrec-conf.org/proceedings/lrec2006/pdf/86_pdf.pdf) (Xia et al., LREC 2006)
ACL