@inproceedings{lapshinova-koltunski-etal-2022-parcorfull2,
title = "{P}ar{C}or{F}ull2.0: a Parallel Corpus Annotated with Full Coreference",
author = "Lapshinova-Koltunski, Ekaterina and
Ferreira, Pedro Augusto and
Lartaud, Elina and
Hardmeier, Christian",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.85",
pages = "805--813",
abstract = "In this paper, we describe ParCorFull2.0, a parallel corpus annotated with full coreference chains for multiple languages, which is an extension of the existing corpus ParCorFull (Lapshinova-Koltunski et al., 2018). Similar to the previous version, this corpus has been created to address translation of coreference across languages, a phenomenon still challenging for machine translation (MT) and other multilingual natural language processing (NLP) applications. The current version of the corpus that we present here contains not only parallel texts for the language pair English-German, but also for English-French and English-Portuguese, which are all major European languages. The new language pairs belong to the Romance languages. The addition of a new language group creates a need of extension not only in terms of texts added, but also in terms of the annotation guidelines. Both French and Portuguese contain structures not found in English and German. Moreover, Portuguese is a pro-drop language bringing even more systemic differences in the realisation of coreference into our cross-lingual resources. These differences cause problems for multilingual coreference resolution and machine translation. Our parallel corpus with full annotation of coreference will be a valuable resource with a variety of uses not only for NLP applications, but also for contrastive linguists and researchers in translation studies.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lapshinova-koltunski-etal-2022-parcorfull2">
<titleInfo>
<title>ParCorFull2.0: a Parallel Corpus Annotated with Full Coreference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Lapshinova-Koltunski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pedro</namePart>
<namePart type="given">Augusto</namePart>
<namePart type="family">Ferreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elina</namePart>
<namePart type="family">Lartaud</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Hardmeier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</namePart>
<namePart type="family">Mazo</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we describe ParCorFull2.0, a parallel corpus annotated with full coreference chains for multiple languages, which is an extension of the existing corpus ParCorFull (Lapshinova-Koltunski et al., 2018). Similar to the previous version, this corpus has been created to address translation of coreference across languages, a phenomenon still challenging for machine translation (MT) and other multilingual natural language processing (NLP) applications. The current version of the corpus that we present here contains not only parallel texts for the language pair English-German, but also for English-French and English-Portuguese, which are all major European languages. The new language pairs belong to the Romance languages. The addition of a new language group creates a need of extension not only in terms of texts added, but also in terms of the annotation guidelines. Both French and Portuguese contain structures not found in English and German. Moreover, Portuguese is a pro-drop language bringing even more systemic differences in the realisation of coreference into our cross-lingual resources. These differences cause problems for multilingual coreference resolution and machine translation. Our parallel corpus with full annotation of coreference will be a valuable resource with a variety of uses not only for NLP applications, but also for contrastive linguists and researchers in translation studies.</abstract>
<identifier type="citekey">lapshinova-koltunski-etal-2022-parcorfull2</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.85</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>805</start>
<end>813</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ParCorFull2.0: a Parallel Corpus Annotated with Full Coreference
%A Lapshinova-Koltunski, Ekaterina
%A Ferreira, Pedro Augusto
%A Lartaud, Elina
%A Hardmeier, Christian
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F lapshinova-koltunski-etal-2022-parcorfull2
%X In this paper, we describe ParCorFull2.0, a parallel corpus annotated with full coreference chains for multiple languages, which is an extension of the existing corpus ParCorFull (Lapshinova-Koltunski et al., 2018). Similar to the previous version, this corpus has been created to address translation of coreference across languages, a phenomenon still challenging for machine translation (MT) and other multilingual natural language processing (NLP) applications. The current version of the corpus that we present here contains not only parallel texts for the language pair English-German, but also for English-French and English-Portuguese, which are all major European languages. The new language pairs belong to the Romance languages. The addition of a new language group creates a need of extension not only in terms of texts added, but also in terms of the annotation guidelines. Both French and Portuguese contain structures not found in English and German. Moreover, Portuguese is a pro-drop language bringing even more systemic differences in the realisation of coreference into our cross-lingual resources. These differences cause problems for multilingual coreference resolution and machine translation. Our parallel corpus with full annotation of coreference will be a valuable resource with a variety of uses not only for NLP applications, but also for contrastive linguists and researchers in translation studies.
%U https://aclanthology.org/2022.lrec-1.85
%P 805-813
Markdown (Informal)
[ParCorFull2.0: a Parallel Corpus Annotated with Full Coreference](https://aclanthology.org/2022.lrec-1.85) (Lapshinova-Koltunski et al., LREC 2022)
ACL
- Ekaterina Lapshinova-Koltunski, Pedro Augusto Ferreira, Elina Lartaud, and Christian Hardmeier. 2022. ParCorFull2.0: a Parallel Corpus Annotated with Full Coreference. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 805–813, Marseille, France. European Language Resources Association.