Dataset Open Access

Patent text: code, data, and new measures

Arts; Hou; Gomez


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nmm##2200000uu#4500</leader>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">patent measures</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">natural language processing</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">novelty</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">impact</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">USPTO</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">technological progress</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">innovation</subfield>
  </datafield>
  <controlfield tag="005">20210127132515.0</controlfield>
  <controlfield tag="001">3515985</controlfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Jianan</subfield>
    <subfield code="a">Hou</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Juan-Carlos</subfield>
    <subfield code="a">Gomez</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">5103406708</subfield>
    <subfield code="z">md5:cbef0725269ac2185034a30b365066a9</subfield>
    <subfield code="u">https://zenodo.org/record/3515985/files/100_most_similar_patents.zip</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">80884754</subfield>
    <subfield code="z">md5:025c03d1b7f32acc75e93bc4f6d5aa38</subfield>
    <subfield code="u">https://zenodo.org/record/3515985/files/cosine_similarity.zip</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">903581447</subfield>
    <subfield code="z">md5:b1fe1e41a8da1c7ed8948487c7a1089f</subfield>
    <subfield code="u">https://zenodo.org/record/3515985/files/keywords.zip</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">68494502</subfield>
    <subfield code="z">md5:1a0268bc4a8ca3d83deb072e558990e1</subfield>
    <subfield code="u">https://zenodo.org/record/3515985/files/new_bigrams.zip</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">492689117</subfield>
    <subfield code="z">md5:ee65ce71ae3c02319db065685420f056</subfield>
    <subfield code="u">https://zenodo.org/record/3515985/files/new_keyword_comb_1980_1989.zip</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">351278937</subfield>
    <subfield code="z">md5:166d0b81fc60b8714ae77c230b648295</subfield>
    <subfield code="u">https://zenodo.org/record/3515985/files/new_keyword_comb_1990_1994.zip</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">866116127</subfield>
    <subfield code="z">md5:4621d1f6feaaca64f3adec600a6c624f</subfield>
    <subfield code="u">https://zenodo.org/record/3515985/files/new_keyword_comb_1995_1999.zip</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">774701905</subfield>
    <subfield code="z">md5:fc14065819616aee644b01fa2971b9e7</subfield>
    <subfield code="u">https://zenodo.org/record/3515985/files/new_keyword_comb_2000_2004.zip</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">748119596</subfield>
    <subfield code="z">md5:e7167dc5b23816fbfc1ade0e3e047566</subfield>
    <subfield code="u">https://zenodo.org/record/3515985/files/new_keyword_comb_2005_2009.zip</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">557666537</subfield>
    <subfield code="z">md5:f34e22ad7a57fe8aff646c5ebb08fe12</subfield>
    <subfield code="u">https://zenodo.org/record/3515985/files/new_keyword_comb_2010_2018.zip</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">3089558181</subfield>
    <subfield code="z">md5:764c38f0e64d0bcc20d8f7d709b4cfd1</subfield>
    <subfield code="u">https://zenodo.org/record/3515985/files/new_keyword_comb_all.zip</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">10008180</subfield>
    <subfield code="z">md5:ad9ee88d67e61888fae961fa29894148</subfield>
    <subfield code="u">https://zenodo.org/record/3515985/files/new_keywords.zip</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">113464480</subfield>
    <subfield code="z">md5:ae488e2e3460afdb5df0d7ae12b5a409</subfield>
    <subfield code="u">https://zenodo.org/record/3515985/files/new_trigrams.zip</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">100294986</subfield>
    <subfield code="z">md5:675a63980d9deb10eb2062da80a045ce</subfield>
    <subfield code="u">https://zenodo.org/record/3515985/files/patent_text_measures.zip</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">6306854242</subfield>
    <subfield code="z">md5:5ebdfe48395eec11e4f1a2de9490132e</subfield>
    <subfield code="u">https://zenodo.org/record/3515985/files/patent txt raw.zip</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">46024090902</subfield>
    <subfield code="z">md5:0660f13ff52576b824432ff8c6fbe628</subfield>
    <subfield code="u">https://zenodo.org/record/3515985/files/1000_most_similar_patents.zip</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">535293</subfield>
    <subfield code="z">md5:ce0332320560f80efa6a86fcdbbae986</subfield>
    <subfield code="u">https://zenodo.org/record/3515985/files/0_Data_Description_Zenodo.pdf</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">685</subfield>
    <subfield code="z">md5:aea2752c5e38c3ed96976e9264d88a1a</subfield>
    <subfield code="u">https://zenodo.org/record/3515985/files/greek.txt</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">167</subfield>
    <subfield code="z">md5:5d4d932a407310fabea7e80531a9b467</subfield>
    <subfield code="u">https://zenodo.org/record/3515985/files/symbols.txt</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">394962</subfield>
    <subfield code="z">md5:d42922204201e14c015aecd0f0762bd2</subfield>
    <subfield code="u">https://zenodo.org/record/3515985/files/stopwords.txt</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2020-11-13</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire_data</subfield>
    <subfield code="o">oai:zenodo.org:3515985</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">Sam</subfield>
    <subfield code="0">(orcid)0000-0003-3214-7325</subfield>
    <subfield code="a">Arts</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Patent text: code, data, and new measures</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">https://opendatacommons.org/licenses/by/1.0/</subfield>
    <subfield code="a">Open Data Commons Attribution License v1.0</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2">opendefinition.org</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&lt;p&gt;This Zenodo page describes data collection, processing, and different open access data files related to the text of USPTO patent documents. The document &amp;quot;Data Description Zenodo.pdf&amp;quot;&amp;nbsp;provides more details.&amp;nbsp;If you use the code or data, please cite the following paper:&lt;/p&gt;

&lt;p&gt;Arts S, Hou J, Gomez JC. (2020). Natural language processing to identify the creation and impact of new technologies in patent text: code, data, and new measures. Forthcoming&amp;nbsp;&lt;em&gt;Research Policy&lt;/em&gt;. (&lt;a href="https://doi.org/10.1016/j.respol.2020.104144"&gt;https://doi.org/10.1016/j.respol.2020.104144&lt;/a&gt;)&lt;/p&gt;</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isVersionOf</subfield>
    <subfield code="a">10.5281/zenodo.3515984</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.3515985</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">dataset</subfield>
  </datafield>
</record>
2,671
2,946
views
downloads
All versions This version
Views 2,6712,669
Downloads 2,9462,946
Data volume 6.4 TB6.4 TB
Unique views 2,4022,400
Unique downloads 1,7391,739

Share

Cite as