@inproceedings{dione-etal-2010-design,
title = "Design and Development of Part-of-Speech-Tagging Resources for {W}olof ({N}iger-{C}ongo, spoken in {S}enegal)",
author = "Dione, Cheikh M. Bamba and
Kuhn, Jonas and
Zarrie{\ss}, Sina",
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/333_Paper.pdf",
abstract = "In this paper, we report on the design of a part-of-speech-tagset for Wolof and on the creation of a semi-automatically annotated gold standard. In order to achieve high-quality annotation relatively fast, we first generated an accurate lexicon that draws on existing word and name lists and takes into account inflectional and derivational morphology. The main motivation for the tagged corpus is to obtain data for training automatic taggers with machine learning approaches. Hence, we took machine learning considerations into account during tagset design and we present training experiments as part of this paper. The best automatic tagger achieves an accuracy of 95.2{\%} in cross-validation experiments. We also wanted to create a basis for experimenting with annotation projection techniques, which exploit parallel corpora. For this reason, it was useful to use a part of the Bible as the gold standard corpus, for which sentence-aligned parallel versions in many languages are easy to obtain. We also report on preliminary experiments exploiting a statistical word alignment of the parallel text.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dione-etal-2010-design">
<titleInfo>
<title>Design and Development of Part-of-Speech-Tagging Resources for Wolof (Niger-Congo, spoken in Senegal)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cheikh</namePart>
<namePart type="given">M</namePart>
<namePart type="given">Bamba</namePart>
<namePart type="family">Dione</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonas</namePart>
<namePart type="family">Kuhn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sina</namePart>
<namePart type="family">Zarrieß</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>In this paper, we report on the design of a part-of-speech-tagset for Wolof and on the creation of a semi-automatically annotated gold standard. In order to achieve high-quality annotation relatively fast, we first generated an accurate lexicon that draws on existing word and name lists and takes into account inflectional and derivational morphology. The main motivation for the tagged corpus is to obtain data for training automatic taggers with machine learning approaches. Hence, we took machine learning considerations into account during tagset design and we present training experiments as part of this paper. The best automatic tagger achieves an accuracy of 95.2% in cross-validation experiments. We also wanted to create a basis for experimenting with annotation projection techniques, which exploit parallel corpora. For this reason, it was useful to use a part of the Bible as the gold standard corpus, for which sentence-aligned parallel versions in many languages are easy to obtain. We also report on preliminary experiments exploiting a statistical word alignment of the parallel text.</abstract>
<identifier type="citekey">dione-etal-2010-design</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/333_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Design and Development of Part-of-Speech-Tagging Resources for Wolof (Niger-Congo, spoken in Senegal)
%A Dione, Cheikh M. Bamba
%A Kuhn, Jonas
%A Zarrieß, Sina
%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 dione-etal-2010-design
%X In this paper, we report on the design of a part-of-speech-tagset for Wolof and on the creation of a semi-automatically annotated gold standard. In order to achieve high-quality annotation relatively fast, we first generated an accurate lexicon that draws on existing word and name lists and takes into account inflectional and derivational morphology. The main motivation for the tagged corpus is to obtain data for training automatic taggers with machine learning approaches. Hence, we took machine learning considerations into account during tagset design and we present training experiments as part of this paper. The best automatic tagger achieves an accuracy of 95.2% in cross-validation experiments. We also wanted to create a basis for experimenting with annotation projection techniques, which exploit parallel corpora. For this reason, it was useful to use a part of the Bible as the gold standard corpus, for which sentence-aligned parallel versions in many languages are easy to obtain. We also report on preliminary experiments exploiting a statistical word alignment of the parallel text.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/333_Paper.pdf
Markdown (Informal)
[Design and Development of Part-of-Speech-Tagging Resources for Wolof (Niger-Congo, spoken in Senegal)](http://www.lrec-conf.org/proceedings/lrec2010/pdf/333_Paper.pdf) (Dione et al., LREC 2010)
ACL