Dataset Open Access

The LAMBADA dataset

Paperno, Denis; Kruszewski, Germán; Lazaridou, Angeliki; Pham, Quan Ngoc; Bernardi, Raffaella; Pezzelle, Sandro; Baroni, Marco; Boleda, Gemma; Fernández, Raquel


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nmm##2200000uu#4500</leader>
  <controlfield tag="005">20191101071202.0</controlfield>
  <controlfield tag="001">2630551</controlfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of Trento</subfield>
    <subfield code="a">Kruszewski, Germán</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of Trento</subfield>
    <subfield code="a">Lazaridou, Angeliki</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of Trento</subfield>
    <subfield code="a">Pham, Quan Ngoc</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of Trento</subfield>
    <subfield code="a">Bernardi, Raffaella</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of Trento</subfield>
    <subfield code="a">Pezzelle, Sandro</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of Trento</subfield>
    <subfield code="a">Baroni, Marco</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of Trento</subfield>
    <subfield code="a">Boleda, Gemma</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of Amsterdam</subfield>
    <subfield code="a">Fernández, Raquel</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">334527694</subfield>
    <subfield code="z">md5:8014f6ba29b80dd27fb853a7373af7c3</subfield>
    <subfield code="u">https://zenodo.org/record/2630551/files/lambada-dataset.tar.gz</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">1717206</subfield>
    <subfield code="z">md5:6d9fcfc38c2068a360597ea63b814045</subfield>
    <subfield code="u">https://zenodo.org/record/2630551/files/rejected-data1.tar.gz</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2016-08-07</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="o">oai:zenodo.org:2630551</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">University of Trento</subfield>
    <subfield code="a">Paperno, Denis</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">The LAMBADA dataset</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">283554</subfield>
    <subfield code="a">Compositional Operations in Semantic Space</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">655577</subfield>
    <subfield code="a">Linking Objects to Vectors in distributional semantics: A framework to anchor corpus-based meaning representations to the external world</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">http://creativecommons.org/licenses/by/4.0/legalcode</subfield>
    <subfield code="a">Creative Commons Attribution 4.0 International</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;We introduce LAMBADA, a dataset to evaluate the capabilities of computational models for text understanding by means of a word prediction task. LAMBADA is a collection of narrative passages sharing the characteristic that human subjects are able to guess their last word if they are exposed to the whole passage, but not if they only see the last sentence preceding the target word. To succeed on LAMBADA, computational models cannot simply rely on local context, but must be able to keep track of information in the broader discourse. We show that LAMBADA exemplifies a wide range of linguistic phenomena, and that none of several state-of-the-art language models reaches accuracy above 1% on this novel benchmark. We thus propose LAMBADA as a challenging test set, meant to encourage the development of new models capable of genuine understanding of broad context in natural language text.&lt;/p&gt;

&lt;p&gt;&amp;nbsp;&lt;/p&gt;

&lt;p&gt;The LAMBADA paper can be found &lt;a href="http://anthology.aclweb.org/P/P16/P16-1144.pdf"&gt;here&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.2630550</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.2630551</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">dataset</subfield>
  </datafield>
</record>
848
265
views
downloads
All versions This version
Views 848853
Downloads 265265
Data volume 76.0 GB76.0 GB
Unique views 784789
Unique downloads 179179

Share

Cite as