Dataset Open Access

bioRxiv 10k

Daniel Ecer


DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="DOI">10.5281/zenodo.3873702</identifier>
  <creators>
    <creator>
      <creatorName>Daniel Ecer</creatorName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0003-0320-4300</nameIdentifier>
    </creator>
  </creators>
  <titles>
    <title>bioRxiv 10k</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2020</publicationYear>
  <subjects>
    <subject>bioRxiv</subject>
    <subject>PDF</subject>
    <subject>XML</subject>
    <subject>JATS</subject>
  </subjects>
  <dates>
    <date dateType="Issued">2020-07-23</date>
  </dates>
  <language>en</language>
  <resourceType resourceTypeGeneral="Dataset"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/3873702</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsDerivedFrom">http://biorxiv.org/tdm</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="References" resourceTypeGeneral="JournalArticle">10.1145/2494266.2494271</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.3873701</relatedIdentifier>
  </relatedIdentifiers>
  <version>1.0.0</version>
  <rightsList>
    <rights rightsURI="https://creativecommons.org/licenses/by/4.0/legalcode">Creative Commons Attribution 4.0 International</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&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;</description>
    <description descriptionType="Other">{"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"]}</description>
  </descriptions>
</resource>
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