Other Open Access

OCR models for Occitan (standard spelling)

Marianne Vergez-Couret


DCAT Export

<?xml version='1.0' encoding='utf-8'?>
<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:adms="http://www.w3.org/ns/adms#" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dct="http://purl.org/dc/terms/" xmlns:dctype="http://purl.org/dc/dcmitype/" xmlns:dcat="http://www.w3.org/ns/dcat#" xmlns:duv="http://www.w3.org/ns/duv#" xmlns:foaf="http://xmlns.com/foaf/0.1/" xmlns:frapo="http://purl.org/cerif/frapo/" xmlns:geo="http://www.w3.org/2003/01/geo/wgs84_pos#" xmlns:gsp="http://www.opengis.net/ont/geosparql#" xmlns:locn="http://www.w3.org/ns/locn#" xmlns:org="http://www.w3.org/ns/org#" xmlns:owl="http://www.w3.org/2002/07/owl#" xmlns:prov="http://www.w3.org/ns/prov#" xmlns:rdfs="http://www.w3.org/2000/01/rdf-schema#" xmlns:schema="http://schema.org/" xmlns:skos="http://www.w3.org/2004/02/skos/core#" xmlns:vcard="http://www.w3.org/2006/vcard/ns#" xmlns:wdrs="http://www.w3.org/2007/05/powder-s#">
  <rdf:Description rdf:about="https://doi.org/10.5281/zenodo.2533877">
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://doi.org/10.5281/zenodo.2533877</dct:identifier>
    <foaf:page rdf:resource="https://doi.org/10.5281/zenodo.2533877"/>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Marianne Vergez-Couret</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Université de Poitiers</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:title>OCR models for Occitan (standard spelling)</dct:title>
    <dct:publisher>
      <foaf:Agent>
        <foaf:name>Zenodo</foaf:name>
      </foaf:Agent>
    </dct:publisher>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#gYear">2019</dct:issued>
    <dcat:keyword>OCR module, Tesseract, Jochre, Occitan, OCR</dcat:keyword>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2019-01-08</dct:issued>
    <owl:sameAs rdf:resource="https://zenodo.org/record/2533877"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/2533877</skos:notation>
        <adms:schemeAgency>url</adms:schemeAgency>
      </adms:Identifier>
    </adms:identifier>
    <dct:isVersionOf rdf:resource="https://doi.org/10.5281/zenodo.2533876"/>
    <dct:isPartOf rdf:resource="https://zenodo.org/communities/restaure"/>
    <owl:versionInfo>1</owl:versionInfo>
    <dct:description>&lt;p&gt;This dataset provides trained Tesseract (&lt;a href="https://github.com/tesseract-ocr/tesseract"&gt;https://github.com/tesseract-ocr/tesseract&lt;/a&gt;) and Jochre (&lt;a href="https://github.com/urieli/jochre"&gt;https://github.com/urieli/jochre&lt;/a&gt;) OCR models for Occitan ( for the standard spelling and two dialects, Gascon and Lengadocian). These models were developed in the context of the RESTAURE project, funded by the French ANR.&amp;nbsp;&lt;/p&gt; &lt;p&gt;Two models are provided. They were presented in the following article &lt;a href="http://hal.archives-ouvertes.fr/hal-01252241"&gt;https://hal.archives-ouvertes.fr/hal-01252241&lt;/a&gt; and also re-evaluated for the creation of another corpus in &lt;a href="https://www.openscience.fr/Constitution-et-annotation-d-un-corpus-ecrit-de-contes-et-recits-en-occitan"&gt;https://www.openscience.fr/Constitution-et-annotation-d-un-corpus-ecrit-de-contes-et-recits-en-occitan&lt;/a&gt;.&lt;/p&gt; &lt;p&gt;The first model for Jochre, JOCHRE_2015, has been trained for Jochre 1.1.2b. The training images and corresponding texts were manually annotated using a Jochre online platform (excerpts from 7 different printed works, totalling about 20,000 words)&lt;/p&gt; &lt;p&gt;The second model for Tesseract, TESS_2015, was trained using the jTessBoxEditor tool (&lt;a href="http://vietocr.sourceforge.net/training.html"&gt;http://vietocr.sourceforge.net/training.html&lt;/a&gt;), Version 1.4 (2 May 2015), based on images automatically generated from the training texts (the one used for Jochre). The generation of the images used a 36pt font size, and two fonts were used (Arial and Times New Roman), with their normal and italic variants. The Tesseract model can be used with Tesseract 3.0x.&lt;/p&gt; &lt;p&gt;List of words was also used for those two trainings. We conflated Occitan words found in several lexicons, dictionaries and corpora for the two dialects, Gascon and Lengadocian:&lt;/p&gt; &lt;ul&gt; &lt;li&gt;Lexicon extracted from 60 literary works (from 29 different authors) gathered in the BaTel&amp;Ograve;c project.&lt;/li&gt; &lt;li&gt;Dictonary entries from &lt;em&gt;Dictionnaire Fran&amp;ccedil;ais/Occitan Gascon Toulousain&lt;/em&gt; de Nicolau Rei B&amp;egrave;thv&amp;eacute;der, 2004, IEO Edicions&lt;/li&gt; &lt;li&gt;Dictonary entries from &lt;em&gt;Dictionnaire Fran&amp;ccedil;ais/Occitan&lt;/em&gt; de Cristian Laus, 2004, IEO/IDECO&lt;/li&gt; &lt;li&gt;Dictonary entries from &lt;em&gt;Dictionnaire Fran&amp;ccedil;ais/Occitan (Gascon)&lt;/em&gt; de Miqu&amp;egrave;u Grosclaude, Gilab&amp;egrave;rt Nari&amp;ograve;o e Patric Guilhemjoan, 2007, Per Noste Edicions&lt;/li&gt; &lt;li&gt;Conjugated forms from Verb&amp;rsquo;&amp;Ograve;c (designed by the &lt;em&gt;Congr&amp;egrave;s permanent de la lenga occitana&lt;/em&gt; (&lt;a href="http://www.locongres.org"&gt;http://www.locongres.org&lt;/a&gt;))&lt;/li&gt; &lt;li&gt;List of proper nouns extracted from the Apertium (free/open-source machine translation platform) Occitan lexicon.&lt;/li&gt; &lt;/ul&gt; &lt;p&gt;The jochre model can be used with the Jochre software (&lt;a href="https://github.com/urieli/jochre"&gt;https://github.com/urieli/jochre&lt;/a&gt;). See also Jochre wiki (https://github.com/urieli/jochre/wiki).&lt;/p&gt; &lt;p&gt;The Tesseract models can be used&amp;nbsp; for instance using the gImageReader tool (&lt;a href="https://github.com/manisandro/gImageReader"&gt;https://github.com/manisandro/gImageReader&lt;/a&gt;), which provides a graphical user interface for the Tesseract tool.&amp;nbsp;&lt;/p&gt; &lt;p&gt;When evaluated against the same test corpus (four extracts from four different authors from two dialects, Gascon and Lengadocian), the Jochre model achieves better performance levels.&lt;/p&gt; &lt;p&gt;&amp;nbsp;&lt;/p&gt;</dct:description>
    <dct:accessRights rdf:resource="http://publications.europa.eu/resource/authority/access-right/PUBLIC"/>
    <dct:accessRights>
      <dct:RightsStatement rdf:about="info:eu-repo/semantics/openAccess">
        <rdfs:label>Open Access</rdfs:label>
      </dct:RightsStatement>
    </dct:accessRights>
    <dct:license rdf:resource="https://creativecommons.org/licenses/by/4.0/legalcode"/>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL>https://doi.org/10.5281/zenodo.2533877</dcat:accessURL>
        <dcat:byteSize>5040156</dcat:byteSize>
        <dcat:downloadURL>https://zenodo.org/record/2533877/files/JOCHRE_2015.zip</dcat:downloadURL>
        <dcat:mediaType>application/zip</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL>https://doi.org/10.5281/zenodo.2533877</dcat:accessURL>
        <dcat:byteSize>3182964</dcat:byteSize>
        <dcat:downloadURL>https://zenodo.org/record/2533877/files/TESS_2015.traineddata</dcat:downloadURL>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
</rdf:RDF>
145
22
views
downloads
All versions This version
Views 145145
Downloads 2221
Data volume 90.5 MB85.4 MB
Unique views 136136
Unique downloads 2019

Share

Cite as