@inproceedings{ferreira-etal-2014-casa,
title = "Casa de la Lh{\'e}ngua: a set of language resources and natural language processing tools for {M}irandese",
author = "Ferreira, Jos{\'e} Pedro and
Chesi, Cristiano and
Baldewijns, Daan and
Pinto, Fernando Miguel and
Correia, Margarita and
Braga, Daniela and
Cho, Hyongsil and
Ferreira, Amadeu and
Dias, Miguel",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/1174_Paper.pdf",
pages = "536--540",
abstract = "This paper describes the efforts for the construction of Language Resources and NLP tools for Mirandese, a minority language spoken in North-eastern Portugal, now available on a community-led portal, Casa de la Lh{\'e}ngua. The resources were developed in the context of a collaborative citizenship project led by Microsoft, in the context of the creation of the first TTS system for Mirandese. Development efforts encompassed the compilation of a corpus with over 1M tokens, the construction of a GTP system, syllable-division, inflection and a Part-of-Speech (POS) tagger modules, leading to the creation of an inflected lexicon of about 200.000 entries with phonetic transcription, detailed POS tagging, syllable division, and stress mark-up. Alongside these tasks, which were made easier through the adaptation and reuse of existing tools for closely related languages, a casting for voice talents among the speaking community was conducted and the first speech database for speech synthesis was recorded for Mirandese. These resources were combined to fulfil the requirements of a well-tested statistical parameter synthesis model, leading to an intelligible voice font. These language resources are available freely at Casa de la Lh{\'e}ngua, aiming at promoting the development of real-life applications and fostering linguistic research on Mirandese.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ferreira-etal-2014-casa">
<titleInfo>
<title>Casa de la Lhéngua: a set of language resources and natural language processing tools for Mirandese</title>
</titleInfo>
<name type="personal">
<namePart type="given">José</namePart>
<namePart type="given">Pedro</namePart>
<namePart type="family">Ferreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cristiano</namePart>
<namePart type="family">Chesi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daan</namePart>
<namePart type="family">Baldewijns</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fernando</namePart>
<namePart type="given">Miguel</namePart>
<namePart type="family">Pinto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Margarita</namePart>
<namePart type="family">Correia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniela</namePart>
<namePart type="family">Braga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyongsil</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amadeu</namePart>
<namePart type="family">Ferreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miguel</namePart>
<namePart type="family">Dias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the efforts for the construction of Language Resources and NLP tools for Mirandese, a minority language spoken in North-eastern Portugal, now available on a community-led portal, Casa de la Lhéngua. The resources were developed in the context of a collaborative citizenship project led by Microsoft, in the context of the creation of the first TTS system for Mirandese. Development efforts encompassed the compilation of a corpus with over 1M tokens, the construction of a GTP system, syllable-division, inflection and a Part-of-Speech (POS) tagger modules, leading to the creation of an inflected lexicon of about 200.000 entries with phonetic transcription, detailed POS tagging, syllable division, and stress mark-up. Alongside these tasks, which were made easier through the adaptation and reuse of existing tools for closely related languages, a casting for voice talents among the speaking community was conducted and the first speech database for speech synthesis was recorded for Mirandese. These resources were combined to fulfil the requirements of a well-tested statistical parameter synthesis model, leading to an intelligible voice font. These language resources are available freely at Casa de la Lhéngua, aiming at promoting the development of real-life applications and fostering linguistic research on Mirandese.</abstract>
<identifier type="citekey">ferreira-etal-2014-casa</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/1174_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>536</start>
<end>540</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Casa de la Lhéngua: a set of language resources and natural language processing tools for Mirandese
%A Ferreira, José Pedro
%A Chesi, Cristiano
%A Baldewijns, Daan
%A Pinto, Fernando Miguel
%A Correia, Margarita
%A Braga, Daniela
%A Cho, Hyongsil
%A Ferreira, Amadeu
%A Dias, Miguel
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F ferreira-etal-2014-casa
%X This paper describes the efforts for the construction of Language Resources and NLP tools for Mirandese, a minority language spoken in North-eastern Portugal, now available on a community-led portal, Casa de la Lhéngua. The resources were developed in the context of a collaborative citizenship project led by Microsoft, in the context of the creation of the first TTS system for Mirandese. Development efforts encompassed the compilation of a corpus with over 1M tokens, the construction of a GTP system, syllable-division, inflection and a Part-of-Speech (POS) tagger modules, leading to the creation of an inflected lexicon of about 200.000 entries with phonetic transcription, detailed POS tagging, syllable division, and stress mark-up. Alongside these tasks, which were made easier through the adaptation and reuse of existing tools for closely related languages, a casting for voice talents among the speaking community was conducted and the first speech database for speech synthesis was recorded for Mirandese. These resources were combined to fulfil the requirements of a well-tested statistical parameter synthesis model, leading to an intelligible voice font. These language resources are available freely at Casa de la Lhéngua, aiming at promoting the development of real-life applications and fostering linguistic research on Mirandese.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/1174_Paper.pdf
%P 536-540
Markdown (Informal)
[Casa de la Lhéngua: a set of language resources and natural language processing tools for Mirandese](http://www.lrec-conf.org/proceedings/lrec2014/pdf/1174_Paper.pdf) (Ferreira et al., LREC 2014)
ACL
- José Pedro Ferreira, Cristiano Chesi, Daan Baldewijns, Fernando Miguel Pinto, Margarita Correia, Daniela Braga, Hyongsil Cho, Amadeu Ferreira, and Miguel Dias. 2014. Casa de la Lhéngua: a set of language resources and natural language processing tools for Mirandese. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 536–540, Reykjavik, Iceland. European Language Resources Association (ELRA).