Dataset Open Access

bioRxiv 10k

Daniel Ecer


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.3873702">
    <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.3873702</dct:identifier>
    <foaf:page rdf:resource="https://doi.org/10.5281/zenodo.3873702"/>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0003-0320-4300">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0003-0320-4300</dct:identifier>
        <foaf:name>Daniel Ecer</foaf:name>
      </rdf:Description>
    </dct:creator>
    <dct:title>bioRxiv 10k</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">2020</dct:issued>
    <dcat:keyword>bioRxiv</dcat:keyword>
    <dcat:keyword>PDF</dcat:keyword>
    <dcat:keyword>XML</dcat:keyword>
    <dcat:keyword>JATS</dcat:keyword>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2020-07-23</dct:issued>
    <dct:language rdf:resource="http://publications.europa.eu/resource/authority/language/ENG"/>
    <owl:sameAs rdf:resource="https://zenodo.org/record/3873702"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/3873702</skos:notation>
        <adms:schemeAgency>url</adms:schemeAgency>
      </adms:Identifier>
    </adms:identifier>
    <dct:source rdf:resource="http://biorxiv.org/tdm"/>
    <dct:references rdf:resource="https://doi.org/10.1145/2494266.2494271"/>
    <dct:isVersionOf rdf:resource="https://doi.org/10.5281/zenodo.3873701"/>
    <owl:versionInfo>1.0.0</owl:versionInfo>
    <dct:description>&lt;p&gt;This dataset is a CC-BY 4.0 subset of what bioRxiv kindly made available: &lt;a href="https://www.biorxiv.org/tdm"&gt;https://www.biorxiv.org/tdm&lt;/a&gt;&lt;/p&gt; &lt;p&gt;It is randomized and split into train (6,000), validation (2,000) and test (2,000) subsets - 10,000 PDF / XML pairs in total.&lt;/p&gt; &lt;p&gt;The zip files further contain file lists of smaller subsets that used the subject area to potentially create a balanced subset.&lt;/p&gt; &lt;p&gt;The zip is similar in structure to the &amp;quot;PMC sample 1943&amp;quot; dataset that was created as part of: &lt;a href="https://doi.org/10.1145/2494266.2494271"&gt;https://doi.org/10.1145/2494266.2494271&lt;/a&gt; (a working link is available from: &lt;a href="https://grobid.readthedocs.io/en/stable/End-to-end-evaluation/"&gt;https://grobid.readthedocs.io/en/stable/End-to-end-evaluation/&lt;/a&gt;).&lt;/p&gt; &lt;p&gt;Therefore it is well suited for evaluation of &lt;a href="https://github.com/elifesciences/sciencebeam/wiki/Related-Projects"&gt;PDF to XML conversion tools&lt;/a&gt;, such as &lt;a href="https://github.com/kermitt2/grobid"&gt;GROBID&lt;/a&gt;. The dataset was created as part of &lt;a href="https://elifesciences.org/"&gt;eLife&lt;/a&gt;&amp;#39;s &lt;a href="https://github.com/elifesciences/sciencebeam"&gt;ScienceBeam&lt;/a&gt; project.&lt;/p&gt;</dct:description>
    <dct:description>{"references": ["Constantin, A., Steve, P., Andrei, V.: Fully-automated PDF-to-XML conversion of scientific literature. In: Proceedings of the ACM Symposium on Document Engineering, pp. 177\u2013180. ACM, New York (2013). doi: 10.1145/2494266.2494271"]}</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.3873702"/>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.3873702">https://doi.org/10.5281/zenodo.3873702</dcat:accessURL>
        <dcat:byteSize>5738592606</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/3873702/files/biorxiv-10k-test-2000.zip">https://zenodo.org/record/3873702/files/biorxiv-10k-test-2000.zip</dcat:downloadURL>
        <dcat:mediaType>application/zip</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.3873702">https://doi.org/10.5281/zenodo.3873702</dcat:accessURL>
        <dcat:byteSize>17233894299</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/3873702/files/biorxiv-10k-train-6000.zip">https://zenodo.org/record/3873702/files/biorxiv-10k-train-6000.zip</dcat:downloadURL>
        <dcat:mediaType>application/zip</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.3873702">https://doi.org/10.5281/zenodo.3873702</dcat:accessURL>
        <dcat:byteSize>5811669057</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/3873702/files/biorxiv-10k-validation-2000.zip">https://zenodo.org/record/3873702/files/biorxiv-10k-validation-2000.zip</dcat:downloadURL>
        <dcat:mediaType>application/zip</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
</rdf:RDF>
131
19,738
views
downloads
All versions This version
Views 131131
Downloads 19,73819,738
Data volume 262.6 TB262.6 TB
Unique views 118118
Unique downloads 1,5901,590

Share

Cite as