<ddi:DDIInstance xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="ddi:instance:3_3 http://ddialliance.org/Specification/DDI-Lifecycle/3.3/XMLSchema/instance.xsd" xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:ddi="ddi:instance:3_3" xmlns:r="ddi:reusable:3_3" xmlns:s="ddi:studyunit:3_3" xmlns:d="ddi:datacollection:3_3" xmlns:a="ddi:archive:3_3" xmlns:c="ddi:conceptualcomponent:3_3" xmlns:cm="ddi:comparative:3_3" xmlns:g="ddi:group:3_3" xmlns:l="ddi:logicalproduct:3_3" xmlns:p="ddi:physicaldataproduct:3_3" xmlns:pi="ddi:physicalinstance:3_3" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:xhtml="http://www.w3.org/1999/xhtml" xmlns:xml="http://www.w3.org/XML/1998/namespace" isMaintainable="true" scopeOfUniqueness="Agency">
  <r:URN>urn:ddi:se.researchdata:2022-157-1:1</r:URN>
  <r:Agency>SND</r:Agency>
  <r:ID>2022-157-1</r:ID>
  <r:Version>1</r:Version>
  <g:ResourcePackage>
    <r:URN>urn:ddi:se.researchdata:2022-157-1.ResourcePackage:2.0</r:URN>
    <r:OtherMaterialScheme>
      <r:URN>urn:ddi:se.researchdata:2022-157-1.OtherMaterialScheme:2.0</r:URN>
    </r:OtherMaterialScheme>
    <a:OrganizationScheme>
      <r:URN>urn:ddi:se.researchdata:2022-157-1.OrganizationScheme-0:2.0</r:URN>
      <a:Individual>
        <r:URN>urn:ddi:se.researchdata:2022-157-1.Individual-0:2.0</r:URN>
        <r:UserAttributePair>
          <r:AttributeKey>affiliation</r:AttributeKey>
          <r:AttributeValue>Uppsala University</r:AttributeValue>
        </r:UserAttributePair>
        <a:IndividualIdentification>
          <a:IndividualName>
            <a:FirstGiven>Gabriel</a:FirstGiven>
            <a:LastFamily>Westman</a:LastFamily>
            <a:FullName>
              <r:String>Gabriel Westman</r:String>
            </a:FullName>
          </a:IndividualName>
          <a:ResearcherID>
            <a:TypeOfID>ORCID</a:TypeOfID>
            <a:ResearcherIdentification>0000-0001-9402-772X</a:ResearcherIdentification>
          </a:ResearcherID>
        </a:IndividualIdentification>
      </a:Individual>
    </a:OrganizationScheme>
  </g:ResourcePackage>
  <s:StudyUnit>
    <r:URN>urn:ddi:se.researchdata:2022-157-1.StudyUnit:2.0</r:URN>
    <r:UserID typeOfUserID="datasetIdentifier">2022-157-1</r:UserID>
    <r:Citation>
      <r:Title>
        <r:String xml:lang="sv">Tokeniserad produktinformation för centralt godkända läkemedel inom EU (extraherad 2022-05-03)</r:String>
        <r:String xml:lang="en">Tokenized product information for centrally approved medicines within EU (extracted May 3, 2022)</r:String>
      </r:Title>
      <r:Creator>
        <r:CreatorReference>
          <r:URN>urn:ddi:se.researchdata:2022-157-1.Individual-0:2.0</r:URN>
          <r:TypeOfObject>Individual</r:TypeOfObject>
        </r:CreatorReference>
      </r:Creator>
      <r:Publisher>
        <r:PublisherName>
          <r:String xml:lang="sv">Uppsala universitet</r:String>
          <r:String xml:lang="en">Uppsala University</r:String>
        </r:PublisherName>
      </r:Publisher>
      <r:Publisher>
        <r:PublisherName>
          <r:String xml:lang="sv">Uppsala universitet</r:String>
          <r:String xml:lang="en">Uppsala University</r:String>
        </r:PublisherName>
      </r:Publisher>
      <r:PublicationDate>
        <r:SimpleDate>2022-09-29</r:SimpleDate>
      </r:PublicationDate>
      <r:InternationalIdentifier>
        <r:IdentifierContent>10.57804/ggrw-hr06</r:IdentifierContent>
        <r:ManagingAgency controlledVocabularyAgencyName="DOI">DOI</r:ManagingAgency>
      </r:InternationalIdentifier>
    </r:Citation>
    <r:Abstract>
      <r:Content xml:lang="sv">Tokeniserad produktinformation för centralt godkända läkemedel inom EU. Se engelsk beskrivning för detaljer om hur data kompilerats och bearbetats.

Databasen innehåller tokeniserad produktinformation på meningsnivå, extraherad från alla centralt godkända läkemedel inom EU (2022-05-03). Se engelskspråkig beskrivning för ytterligare detaljer.</r:Content>
      <r:Content xml:lang="en">The text corpus was compiled on May 3, 2022, by scripted downloading of all available English language product information files for all centrally approved medicinal products within the EU, from the European Medicines Agency website. Package Leaflet (PL) and Summary of product characteristics (SmPC) documents for each medicinal product, excluding multiplicate documents for medicinal products with more than one strength or pharmaceutical preparation, were used. The PDF files were scraped using the pdfplumber version 0.6.1 package in Python 3.8.10 to extract all text except page numbering, headers, and footers. 

Line breaks and special characters (excluding punctuation characters) were removed, and punctuation was added to sentences where this was missing (such as headings) to avoid false aggregation. All paragraphs were tokenized on a sentence level using the Natural Language Toolkit (NLTK) version 3.7 tokenizer

This database contains sentence-level tokenized product infomation from all centrally approved medicinal products within the EU (May 3, 2022) including Summary of product characteristics (SmPC) and Package leaflet (PL) documents.

A total of 1258 medicinal products were initially included, of which 5 were subsequently excluded due to document compatibility issues. From these, a total of 783 K sentences were extracted from PL and SmPC documents.</r:Content>
    </r:Abstract>
    <r:Coverage>
      <r:TopicalCoverage>
        <r:URN>urn:ddi:se.researchdata:2022-157-1.TopicalCoverage:2.0</r:URN>
        <r:Subject xml:lang="en" controlledVocabularyID="102" controlledVocabularyName="Standard för svensk indelning av forskningsämnen 2025">Computer and Information Sciences</r:Subject>
        <r:Subject xml:lang="sv" controlledVocabularyID="102" controlledVocabularyName="Standard för svensk indelning av forskningsämnen 2025">Data- och informationsvetenskap (datateknik)</r:Subject>
        <r:Subject xml:lang="en" controlledVocabularyID="301" controlledVocabularyName="Standard för svensk indelning av forskningsämnen 2025">Basic Medicine</r:Subject>
        <r:Subject xml:lang="sv" controlledVocabularyID="301" controlledVocabularyName="Standard för svensk indelning av forskningsämnen 2025">Medicinska och farmaceutiska grundvetenskaper</r:Subject>
        <r:Keyword xml:lang="en" controlledVocabularyID="D007254" controlledVocabularyName="MeSH">Information Science</r:Keyword>
        <r:Keyword xml:lang="sv" controlledVocabularyID="D007254" controlledVocabularyName="MeSH">Informationsvetenskap</r:Keyword>
        <r:Keyword xml:lang="en" controlledVocabularyID="urn:ddi:int.cessda.elsst:da8c6947-2999-41bf-914b-9360015e85c6:4" controlledVocabularyName="ELSST">LINGUISTICS</r:Keyword>
        <r:Keyword xml:lang="sv" controlledVocabularyID="urn:ddi:int.cessda.elsst:da8c6947-2999-41bf-914b-9360015e85c6:4" controlledVocabularyName="ELSST">LINGVISTIK</r:Keyword>
        <r:Keyword xml:lang="en" controlledVocabularyID="D001185" controlledVocabularyName="MeSH">Artificial Intelligence</r:Keyword>
        <r:Keyword xml:lang="sv" controlledVocabularyID="D001185" controlledVocabularyName="MeSH">Artificiell intelligens</r:Keyword>
        <r:Keyword xml:lang="en" controlledVocabularyID="D010604" controlledVocabularyName="MeSH">Pharmacy</r:Keyword>
        <r:Keyword xml:lang="sv" controlledVocabularyID="D010604" controlledVocabularyName="MeSH">Farmaci</r:Keyword>
      </r:TopicalCoverage>
      <r:SpatialCoverage />
    </r:Coverage>
    <a:Archive>
      <r:URN>urn:ddi:se.researchdata:2022-157-1.Archive:2.0</r:URN>
      <a:ArchiveSpecific>
        <a:Item>
          <a:Access>
            <r:URN>urn:ddi:se.researchdata:2022-157-1.Archive-ArchiveSpecificType-AccessType:2.0</r:URN>
            <a:TypeOfAccess controlledVocabularyName="info:eu-repo-Access-Terms vocabulary">openAccess</a:TypeOfAccess>
          </a:Access>
          <a:DataFileQuantity>3</a:DataFileQuantity>
        </a:Item>
      </a:ArchiveSpecific>
    </a:Archive>
  </s:StudyUnit>
</ddi:DDIInstance>