@inproceedings{xu-etal-2012-grammar,
title = "A Grammar-informed Corpus-based Sentence Database for Linguistic and Computational Studies",
author = "Xu, Hongzhi and
Chen, Helen Kaiyun and
Huang, Chu-Ren and
Lu, Qin and
Shi, Dingxu and
Chiu, Tin-Shing",
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/401_Paper.pdf",
pages = "3140--3144",
abstract = "We adopt the corpus-informed approach to example sentence selections for the construction of a reference grammar. In the process, a database containing sentences that are carefully selected by linguistic experts including the full range of linguistic facts covered in an authoritative Chinese Reference Grammar is constructed and structured according to the reference grammar. A search engine system is developed to facilitate the process of finding the most typical examples the users need to study a linguistic problem or prove their hypotheses. The database can also be used as a training corpus by computational linguists to train models for Chinese word segmentation, POS tagging and sentence parsing.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2012-grammar">
<titleInfo>
<title>A Grammar-informed Corpus-based Sentence Database for Linguistic and Computational Studies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hongzhi</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helen</namePart>
<namePart type="given">Kaiyun</namePart>
<namePart type="family">Chen</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>
<name type="personal">
<namePart type="given">Qin</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dingxu</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tin-Shing</namePart>
<namePart type="family">Chiu</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>We adopt the corpus-informed approach to example sentence selections for the construction of a reference grammar. In the process, a database containing sentences that are carefully selected by linguistic experts including the full range of linguistic facts covered in an authoritative Chinese Reference Grammar is constructed and structured according to the reference grammar. A search engine system is developed to facilitate the process of finding the most typical examples the users need to study a linguistic problem or prove their hypotheses. The database can also be used as a training corpus by computational linguists to train models for Chinese word segmentation, POS tagging and sentence parsing.</abstract>
<identifier type="citekey">xu-etal-2012-grammar</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/401_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3140</start>
<end>3144</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Grammar-informed Corpus-based Sentence Database for Linguistic and Computational Studies
%A Xu, Hongzhi
%A Chen, Helen Kaiyun
%A Huang, Chu-Ren
%A Lu, Qin
%A Shi, Dingxu
%A Chiu, Tin-Shing
%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 xu-etal-2012-grammar
%X We adopt the corpus-informed approach to example sentence selections for the construction of a reference grammar. In the process, a database containing sentences that are carefully selected by linguistic experts including the full range of linguistic facts covered in an authoritative Chinese Reference Grammar is constructed and structured according to the reference grammar. A search engine system is developed to facilitate the process of finding the most typical examples the users need to study a linguistic problem or prove their hypotheses. The database can also be used as a training corpus by computational linguists to train models for Chinese word segmentation, POS tagging and sentence parsing.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/401_Paper.pdf
%P 3140-3144
Markdown (Informal)
[A Grammar-informed Corpus-based Sentence Database for Linguistic and Computational Studies](http://www.lrec-conf.org/proceedings/lrec2012/pdf/401_Paper.pdf) (Xu et al., LREC 2012)
ACL