Dataset Open Access

Claim Detection and Matching for Indian Languages

Ashkan Kazemi; Kiran Garimella; Devin Gaffney; Scott A. Hale


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.4890950">
    <rdf:type rdf:resource="http://www.w3.org/ns/dcat#Dataset"/>
    <dct:type rdf:resource="http://purl.org/dc/dcmitype/Dataset"/>
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://doi.org/10.5281/zenodo.4890950</dct:identifier>
    <foaf:page rdf:resource="https://doi.org/10.5281/zenodo.4890950"/>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Ashkan Kazemi</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Michigan &amp; Meedan</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Kiran Garimella</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>MIT</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Devin Gaffney</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Meedan</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Scott A. Hale</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Oxford &amp; Meedan</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:title>Claim Detection and Matching for Indian Languages</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">2021</dct:issued>
    <dcat:keyword>nlp</dcat:keyword>
    <dcat:keyword>fact-checking</dcat:keyword>
    <dcat:keyword>misinformation</dcat:keyword>
    <dcat:keyword>multilingual</dcat:keyword>
    <dcat:keyword>claim matching</dcat:keyword>
    <dcat:keyword>claim detection</dcat:keyword>
    <dcat:keyword>whatsapp</dcat:keyword>
    <dcat:keyword>tamil</dcat:keyword>
    <dcat:keyword>malayalam</dcat:keyword>
    <dcat:keyword>bengali</dcat:keyword>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2021-06-01</dct:issued>
    <dct:language rdf:resource="http://publications.europa.eu/resource/authority/language/HI"/>
    <owl:sameAs rdf:resource="https://zenodo.org/record/4890950"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/4890950</skos:notation>
        <adms:schemeAgency>url</adms:schemeAgency>
      </adms:Identifier>
    </adms:identifier>
    <dct:isVersionOf rdf:resource="https://doi.org/10.5281/zenodo.4890949"/>
    <owl:versionInfo>1.0</owl:versionInfo>
    <dct:description>&lt;p&gt;Two datasets are included in this repository: claim matching and claim detection datasets.&amp;nbsp;The collections contain&amp;nbsp;data in 5 languages: Bengali, English, Hindi, Malayalam and Tamil.&lt;/p&gt; &lt;p&gt;The &amp;quot;claim detection&amp;quot;&amp;nbsp;dataset contains textual claims from social media and fact-checking websites annotated for the&amp;nbsp; &amp;quot;fact-check worthiness&amp;quot; of the claims in each message. Data points have one of the three labels of &amp;quot;Yes&amp;quot; (text contains one or more check-worthy claims), &amp;quot;No&amp;quot; and &amp;quot;Probably&amp;quot;.&amp;nbsp;&lt;/p&gt; &lt;p&gt;The &amp;quot;claim matching&amp;quot; dataset is a curated collection of pairs of textual claims from social media and fact-checking websites for the purpose of automatic and multilingual claim matching.&amp;nbsp;Pairs of data have one of the four labels of &amp;quot;Very Similar&amp;quot;, &amp;quot;Somewhat Similar&amp;quot;, &amp;quot;Somewhat Dissimilar&amp;quot; and &amp;quot;Very Dissimilar&amp;quot;.&lt;/p&gt; &lt;p&gt;All personally identifiable information (PII) including phone numbers, email addresses,&amp;nbsp;license plate numbers and addresses have been replaced with general tags (e.g. &amp;lt;PHONE#&amp;gt;, &amp;lt;ADDRESS&amp;gt;, etc)&amp;nbsp;to protect user anonymity. A detailed explanation on the curation and annotation process is provided in our ACL 2021 paper:&amp;nbsp;&lt;br&gt; &lt;a href="https://arxiv.org/abs/2106.00853"&gt;Kazemi, A.; Garimella, K.; Gaffney, D.; and Hale, S. A. 2021. Claim Matching Beyond English to Scale Global Fact-Checking. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics, ACL 2021.&lt;/a&gt;&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>
    <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.4890950"/>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.4890950"/>
        <dcat:byteSize>3110606</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/4890950/files/claim_detection_dataset.csv"/>
        <dcat:mediaType>text/csv</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.4890950"/>
        <dcat:byteSize>4144285</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/4890950/files/claim_matching_dataset.csv"/>
        <dcat:mediaType>text/csv</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
</rdf:RDF>
318
214
views
downloads
All versions This version
Views 318318
Downloads 214214
Data volume 688.4 MB688.4 MB
Unique views 290290
Unique downloads 178178

Share

Cite as