There is a newer version of this record available.

Software Open Access

HeLI-OTS 1.2 with Python examples

Jauhiainen, Tommi; Jauhiainen, Heidi


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.5853116">
    <rdf:type rdf:resource="http://www.w3.org/ns/dcat#Dataset"/>
    <dct:type rdf:resource="http://purl.org/dc/dcmitype/Software"/>
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://doi.org/10.5281/zenodo.5853116</dct:identifier>
    <foaf:page rdf:resource="https://doi.org/10.5281/zenodo.5853116"/>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0002-6474-3570">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0002-6474-3570</dct:identifier>
        <foaf:name>Jauhiainen, Tommi</foaf:name>
        <foaf:givenName>Tommi</foaf:givenName>
        <foaf:familyName>Jauhiainen</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Helsinki</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0002-8227-5627">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0002-8227-5627</dct:identifier>
        <foaf:name>Jauhiainen, Heidi</foaf:name>
        <foaf:givenName>Heidi</foaf:givenName>
        <foaf:familyName>Jauhiainen</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Helsinki</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:title>HeLI-OTS 1.2 with Python examples</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">2022</dct:issued>
    <dcat:keyword>language identification</dcat:keyword>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2022-01-15</dct:issued>
    <dct:language rdf:resource="http://publications.europa.eu/resource/authority/language/ENG"/>
    <owl:sameAs rdf:resource="https://zenodo.org/record/5853116"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/5853116</skos:notation>
        <adms:schemeAgency>url</adms:schemeAgency>
      </adms:Identifier>
    </adms:identifier>
    <dct:isVersionOf rdf:resource="https://doi.org/10.5281/zenodo.4780897"/>
    <owl:versionInfo>1.2</owl:versionInfo>
    <dct:description>&lt;p&gt;HeLI off-the-shelf language identifier with language models for 200 languages.&lt;/p&gt; &lt;p&gt;Usage:&lt;br&gt; java -jar HeLI.jar -r &amp;lt;infile&amp;gt; -w &amp;lt;outfile&amp;gt;&lt;/p&gt; &lt;p&gt;The program will read the &amp;lt;infile&amp;gt; and classify the language of each line as one of the 200 languages it knows&lt;br&gt; and writes the results, one ISO 639-3 code per line, into file &amp;lt;outfile&amp;gt;.&lt;/p&gt; &lt;p&gt;You can use the -c option to make the program print a confidence score for the identification after each language code.&lt;/p&gt; &lt;p&gt;Usage:&lt;br&gt; java -jar HeLI.jar -c -r &amp;lt;infile&amp;gt; -w &amp;lt;outfile&amp;gt;&lt;/p&gt; &lt;p&gt;You can give the list of comma-separated ISO 639-3 identifiers for relevant languages after -l option.&lt;/p&gt; &lt;p&gt;Usage:&lt;br&gt; java -jar HeLI.jar -r &amp;lt;infile&amp;gt; -w &amp;lt;outfile&amp;gt; -l fin,swe,eng&lt;/p&gt; &lt;p&gt;You can give the number of top-scored languages to print after the -t option. (overrides confidence)&lt;/p&gt; &lt;p&gt;Usage:&lt;br&gt; java -jar HeLI.jar -r &amp;lt;infile&amp;gt; -w &amp;lt;outfile&amp;gt; -l fin,swe,eng -t 2&lt;/p&gt; &lt;p&gt;If you omit both of the filenames, the program will read the standard input one line at a time and write the result to standard output.&lt;/p&gt; &lt;p&gt;It can identify c. 3000 sentences per second using one core on a 2021 laptop and around 3 gigabytes of memory.&lt;/p&gt; &lt;p&gt;If you use this program in producing scientific publications, please refer to:&amp;nbsp;&lt;br&gt; &amp;nbsp;@inproceedings{jauhiainen-etal-2017-evaluation,&lt;br&gt; &amp;nbsp; &amp;nbsp; &amp;nbsp;title = &amp;quot;Evaluation of language identification methods using 285 languages&amp;quot;,&lt;br&gt; &amp;nbsp; &amp;nbsp; &amp;nbsp;author = &amp;quot;Jauhiainen, Tommi &amp;nbsp;and&lt;br&gt; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp;Lind{\&amp;#39;e}n, Krister &amp;nbsp;and&lt;br&gt; &amp;nbsp; &amp;nbsp; &amp;nbsp; &amp;nbsp;Jauhiainen, Heidi&amp;quot;,&lt;br&gt; &amp;nbsp; &amp;nbsp; &amp;nbsp;booktitle = &amp;quot;Proceedings of the 21st Nordic Conference on Computational Linguistics&amp;quot;,&lt;br&gt; &amp;nbsp; &amp;nbsp; &amp;nbsp;month = may,&lt;br&gt; &amp;nbsp; &amp;nbsp; &amp;nbsp;year = &amp;quot;2017&amp;quot;,&lt;br&gt; &amp;nbsp; &amp;nbsp; &amp;nbsp;address = &amp;quot;Gothenburg, Sweden&amp;quot;,&lt;br&gt; &amp;nbsp; &amp;nbsp; &amp;nbsp;publisher = &amp;quot;Association for Computational Linguistics&amp;quot;,&lt;br&gt; &amp;nbsp; &amp;nbsp; &amp;nbsp;url = &amp;quot;https://www.aclweb.org/anthology/W17-0221&amp;quot;,&lt;br&gt; &amp;nbsp; &amp;nbsp; &amp;nbsp;pages = &amp;quot;183--191&amp;quot;,&lt;br&gt; &amp;nbsp;}&lt;/p&gt; &lt;p&gt;Producing and publishing this software has been partly supported by The Finnish Research Impact Foundation Tandem Industry Academia -funding in cooperation with Lingsoft.&lt;/p&gt;</dct:description>
    <dct:description>{"references": ["Jauhiainen, Tommi et al. (2017). Evaluation of language identification methods using 285 languages. https://www.aclweb.org/anthology/W17-0221"]}</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>
    <dcat:distribution>
      <dcat:Distribution>
        <dct:license rdf:resource="https://creativecommons.org/licenses/by/4.0/legalcode"/>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.5853116"/>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.5853116"/>
        <dcat:byteSize>13674</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/5853116/files/HeLI.class"/>
        <dcat:mediaType>application/octet-stream</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.5853116"/>
        <dcat:byteSize>44050741</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/5853116/files/HeLI.jar"/>
        <dcat:mediaType>application/x-java-archive</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.5853116"/>
        <dcat:byteSize>22452</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/5853116/files/HeLI.java"/>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.5853116"/>
        <dcat:byteSize>39</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/5853116/files/HeLI.mf"/>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.5853116"/>
        <dcat:byteSize>884</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/5853116/files/languagelist"/>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.5853116"/>
        <dcat:byteSize>44132999</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/5853116/files/LanguageModels.zip"/>
        <dcat:mediaType>application/zip</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.5853116"/>
        <dcat:byteSize>11419</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/5853116/files/LICENSE"/>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.5853116"/>
        <dcat:byteSize>2734</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/5853116/files/README.md"/>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.5853116"/>
        <dcat:byteSize>1003</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/5853116/files/run_HeLI.py"/>
        <dcat:mediaType>text/x-python</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.5853116"/>
        <dcat:byteSize>745</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/5853116/files/supporting_functions.py"/>
        <dcat:mediaType>text/x-python</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
</rdf:RDF>
977
236
views
downloads
All versions This version
Views 977123
Downloads 23658
Data volume 3.0 GB573.2 MB
Unique views 72699
Unique downloads 11424

Share

Cite as