@inproceedings{gonzalez-rubio-etal-2010-saturnalia,
title = "{S}aturnalia: A {L}atin-{C}atalan Parallel Corpus for Statistical {MT}",
author = "Gonz{\'a}lez-Rubio, Jes{\'u}s and
Civera, Jorge and
Juan, Alfons and
Casacuberta, Francisco",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/541_Paper.pdf",
abstract = "Currently, a great effort is being carried out in the digitalisation of large historical document collections for preservation purposes. The documents in these collections are usually written in ancient languages, such as Latin or Greek, which limits the access of the general public to their content due to the language barrier. Therefore, digital libraries aim not only at storing raw images of digitalised documents, but also to annotate them with their corresponding text transcriptions and translations into modern languages. Unfortunately, ancient languages have at their disposal scarce electronic resources to be exploited by natural language processing techniques. This paper describes the compilation process of a novel Latin-Catalan parallel corpus as a new task for statistical machine translation (SMT). Preliminary experimental results are also reported using a state-of-the-art phrase-based SMT system. The results presented in this work reveal the complexity of the task and its challenging, but interesting nature for future development.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gonzalez-rubio-etal-2010-saturnalia">
<titleInfo>
<title>Saturnalia: A Latin-Catalan Parallel Corpus for Statistical MT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jesús</namePart>
<namePart type="family">González-Rubio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorge</namePart>
<namePart type="family">Civera</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alfons</namePart>
<namePart type="family">Juan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francisco</namePart>
<namePart type="family">Casacuberta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">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">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</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">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Currently, a great effort is being carried out in the digitalisation of large historical document collections for preservation purposes. The documents in these collections are usually written in ancient languages, such as Latin or Greek, which limits the access of the general public to their content due to the language barrier. Therefore, digital libraries aim not only at storing raw images of digitalised documents, but also to annotate them with their corresponding text transcriptions and translations into modern languages. Unfortunately, ancient languages have at their disposal scarce electronic resources to be exploited by natural language processing techniques. This paper describes the compilation process of a novel Latin-Catalan parallel corpus as a new task for statistical machine translation (SMT). Preliminary experimental results are also reported using a state-of-the-art phrase-based SMT system. The results presented in this work reveal the complexity of the task and its challenging, but interesting nature for future development.</abstract>
<identifier type="citekey">gonzalez-rubio-etal-2010-saturnalia</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/541_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Saturnalia: A Latin-Catalan Parallel Corpus for Statistical MT
%A González-Rubio, Jesús
%A Civera, Jorge
%A Juan, Alfons
%A Casacuberta, Francisco
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F gonzalez-rubio-etal-2010-saturnalia
%X Currently, a great effort is being carried out in the digitalisation of large historical document collections for preservation purposes. The documents in these collections are usually written in ancient languages, such as Latin or Greek, which limits the access of the general public to their content due to the language barrier. Therefore, digital libraries aim not only at storing raw images of digitalised documents, but also to annotate them with their corresponding text transcriptions and translations into modern languages. Unfortunately, ancient languages have at their disposal scarce electronic resources to be exploited by natural language processing techniques. This paper describes the compilation process of a novel Latin-Catalan parallel corpus as a new task for statistical machine translation (SMT). Preliminary experimental results are also reported using a state-of-the-art phrase-based SMT system. The results presented in this work reveal the complexity of the task and its challenging, but interesting nature for future development.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/541_Paper.pdf
Markdown (Informal)
[Saturnalia: A Latin-Catalan Parallel Corpus for Statistical MT](http://www.lrec-conf.org/proceedings/lrec2010/pdf/541_Paper.pdf) (González-Rubio et al., LREC 2010)
ACL
- Jesús González-Rubio, Jorge Civera, Alfons Juan, and Francisco Casacuberta. 2010. Saturnalia: A Latin-Catalan Parallel Corpus for Statistical MT. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).