@inproceedings{dipper-etal-2012-use,
title = "The Use of Parallel and Comparable Data for Analysis of Abstract Anaphora in {G}erman and {E}nglish",
author = "Dipper, Stefanie and
Seiss, Melanie and
Zinsmeister, Heike",
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/172_Paper.pdf",
pages = "138--145",
abstract = "Parallel corpora ― original texts aligned with their translations ― are a widely used resource in computational linguistics. Translation studies have shown that translated texts often differ systematically from comparable original texts. Translators tend to be faithful to structures of the original texts, resulting in a ''''''``shining through'''''''' of the original language preferences in the translated text. Translators also tend to make their translations most comprehensible with the effect that translated texts can be more explicit than their source texts. Motivated by the need to use a parallel resource for cross-linguistic feature induction in abstract anaphora resolution, this paper investigates properties of English and German texts in the Europarl corpus, taking into account both general features such as sentence length as well as task-dependent features such as the distribution of demonstrative noun phrases. The investigation is based on the entire Europarl corpus as well as on a small subset thereof, which has been manually annotated. The results indicate English translated texts are sufficiently ''''''``authentic'''''''' to be used as training data for anaphora resolution; results for German texts are less conclusive, though.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dipper-etal-2012-use">
<titleInfo>
<title>The Use of Parallel and Comparable Data for Analysis of Abstract Anaphora in German and English</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stefanie</namePart>
<namePart type="family">Dipper</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Melanie</namePart>
<namePart type="family">Seiss</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heike</namePart>
<namePart type="family">Zinsmeister</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>Parallel corpora ― original texts aligned with their translations ― are a widely used resource in computational linguistics. Translation studies have shown that translated texts often differ systematically from comparable original texts. Translators tend to be faithful to structures of the original texts, resulting in a ”””“shining through”””” of the original language preferences in the translated text. Translators also tend to make their translations most comprehensible with the effect that translated texts can be more explicit than their source texts. Motivated by the need to use a parallel resource for cross-linguistic feature induction in abstract anaphora resolution, this paper investigates properties of English and German texts in the Europarl corpus, taking into account both general features such as sentence length as well as task-dependent features such as the distribution of demonstrative noun phrases. The investigation is based on the entire Europarl corpus as well as on a small subset thereof, which has been manually annotated. The results indicate English translated texts are sufficiently ”””“authentic”””” to be used as training data for anaphora resolution; results for German texts are less conclusive, though.</abstract>
<identifier type="citekey">dipper-etal-2012-use</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/172_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>138</start>
<end>145</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Use of Parallel and Comparable Data for Analysis of Abstract Anaphora in German and English
%A Dipper, Stefanie
%A Seiss, Melanie
%A Zinsmeister, Heike
%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 dipper-etal-2012-use
%X Parallel corpora ― original texts aligned with their translations ― are a widely used resource in computational linguistics. Translation studies have shown that translated texts often differ systematically from comparable original texts. Translators tend to be faithful to structures of the original texts, resulting in a ”””“shining through”””” of the original language preferences in the translated text. Translators also tend to make their translations most comprehensible with the effect that translated texts can be more explicit than their source texts. Motivated by the need to use a parallel resource for cross-linguistic feature induction in abstract anaphora resolution, this paper investigates properties of English and German texts in the Europarl corpus, taking into account both general features such as sentence length as well as task-dependent features such as the distribution of demonstrative noun phrases. The investigation is based on the entire Europarl corpus as well as on a small subset thereof, which has been manually annotated. The results indicate English translated texts are sufficiently ”””“authentic”””” to be used as training data for anaphora resolution; results for German texts are less conclusive, though.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/172_Paper.pdf
%P 138-145
Markdown (Informal)
[The Use of Parallel and Comparable Data for Analysis of Abstract Anaphora in German and English](http://www.lrec-conf.org/proceedings/lrec2012/pdf/172_Paper.pdf) (Dipper et al., LREC 2012)
ACL