@inproceedings{baran-etal-2012-annotating,
title = "Annotating dropped pronouns in {C}hinese newswire text",
author = "Baran, Elizabeth and
Yang, Yaqin and
Xue, Nianwen",
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/361_Paper.pdf",
pages = "2795--2799",
abstract = "We propose an annotation framework to explicitly identify dropped subject pronouns in Chinese. We acknowledge and specify 10 concrete pronouns that exist as words in Chinese and 4 abstract pronouns that do not correspond to Chinese words, but that are recognized conceptually, to native Chinese speakers. These abstract pronouns are identified as ''''''``unspecified'''''''', ''''''``pleonastic'''''''', ''''''``event'''''''', and ''''''``existential'''''''' and are argued to exist cross-linguistically. We trained two annotators, fluent in Chinese, and adjudicated their annotations to form a gold standard. We achieved an inter-annotator agreement kappa of .6 and an observed agreement of .7. We found that annotators had the most difficulty with the abstract pronouns, such as ''''''``unspecified'''''''' and ''''''``event'''''''', but we posit that further specification and training has the potential to significantly improve these results. We believe that this annotated data will serve to help improve Machine Translation models that translate from Chinese to a non pro-drop language, like English, that requires all subject pronouns to be explicit.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="baran-etal-2012-annotating">
<titleInfo>
<title>Annotating dropped pronouns in Chinese newswire text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Baran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaqin</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</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 propose an annotation framework to explicitly identify dropped subject pronouns in Chinese. We acknowledge and specify 10 concrete pronouns that exist as words in Chinese and 4 abstract pronouns that do not correspond to Chinese words, but that are recognized conceptually, to native Chinese speakers. These abstract pronouns are identified as ”””“unspecified””””, ”””“pleonastic””””, ”””“event””””, and ”””“existential”””” and are argued to exist cross-linguistically. We trained two annotators, fluent in Chinese, and adjudicated their annotations to form a gold standard. We achieved an inter-annotator agreement kappa of .6 and an observed agreement of .7. We found that annotators had the most difficulty with the abstract pronouns, such as ”””“unspecified”””” and ”””“event””””, but we posit that further specification and training has the potential to significantly improve these results. We believe that this annotated data will serve to help improve Machine Translation models that translate from Chinese to a non pro-drop language, like English, that requires all subject pronouns to be explicit.</abstract>
<identifier type="citekey">baran-etal-2012-annotating</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/361_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2795</start>
<end>2799</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Annotating dropped pronouns in Chinese newswire text
%A Baran, Elizabeth
%A Yang, Yaqin
%A Xue, Nianwen
%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 baran-etal-2012-annotating
%X We propose an annotation framework to explicitly identify dropped subject pronouns in Chinese. We acknowledge and specify 10 concrete pronouns that exist as words in Chinese and 4 abstract pronouns that do not correspond to Chinese words, but that are recognized conceptually, to native Chinese speakers. These abstract pronouns are identified as ”””“unspecified””””, ”””“pleonastic””””, ”””“event””””, and ”””“existential”””” and are argued to exist cross-linguistically. We trained two annotators, fluent in Chinese, and adjudicated their annotations to form a gold standard. We achieved an inter-annotator agreement kappa of .6 and an observed agreement of .7. We found that annotators had the most difficulty with the abstract pronouns, such as ”””“unspecified”””” and ”””“event””””, but we posit that further specification and training has the potential to significantly improve these results. We believe that this annotated data will serve to help improve Machine Translation models that translate from Chinese to a non pro-drop language, like English, that requires all subject pronouns to be explicit.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/361_Paper.pdf
%P 2795-2799
Markdown (Informal)
[Annotating dropped pronouns in Chinese newswire text](http://www.lrec-conf.org/proceedings/lrec2012/pdf/361_Paper.pdf) (Baran et al., LREC 2012)
ACL
- Elizabeth Baran, Yaqin Yang, and Nianwen Xue. 2012. Annotating dropped pronouns in Chinese newswire text. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 2795–2799, Istanbul, Turkey. European Language Resources Association (ELRA).