Dataset Open Access

Don't count, predict! Semantic vectors

Baroni, Marco; Dinu, Georgiana; Kruszewski, Germán


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.2635544</identifier>
  <creators>
    <creator>
      <creatorName>Baroni, Marco</creatorName>
      <givenName>Marco</givenName>
      <familyName>Baroni</familyName>
      <affiliation>University of Trento</affiliation>
    </creator>
    <creator>
      <creatorName>Dinu, Georgiana</creatorName>
      <givenName>Georgiana</givenName>
      <familyName>Dinu</familyName>
      <affiliation>University of Trento</affiliation>
    </creator>
    <creator>
      <creatorName>Kruszewski, Germán</creatorName>
      <givenName>Germán</givenName>
      <familyName>Kruszewski</familyName>
      <affiliation>University of Trento</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Don't count, predict!  Semantic vectors</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2014</publicationYear>
  <dates>
    <date dateType="Issued">2014-06-01</date>
  </dates>
  <resourceType resourceTypeGeneral="Dataset"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/2635544</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.2635543</relatedIdentifier>
  </relatedIdentifiers>
  <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;Semantic vectors associated with the paper &amp;quot;&lt;a href="https://www.aclweb.org/anthology/P14-1023"&gt;Don&amp;#39;t count, predict! A systematic comparison of context-counting vs context-predicting semantics vectors&lt;/a&gt;&amp;quot;&lt;/p&gt;

&lt;p&gt;&lt;strong&gt;Abstract:&lt;/strong&gt; context-predicting models (more commonly known as embeddings or neural language models) are the new kids on the distributional semantics block. Despite the buzz surrounding these models, the literature is still lacking a systematic comparison of the predictive models with classic, count-vector-based distributional semantic approaches. In this paper, we perform such an extensive evaluation, on a wide range of lexical semantics tasks and across many parameter settings. The results, to our own surprise, show that the buzz is fully justified, as the context-predicting models obtain a thorough and resounding victory against their count-based counterparts.&lt;/p&gt;</description>
  </descriptions>
  <fundingReferences>
    <fundingReference>
      <funderName>European Commission</funderName>
      <funderIdentifier funderIdentifierType="Crossref Funder ID">10.13039/501100000780</funderIdentifier>
      <awardNumber awardURI="info:eu-repo/grantAgreement/EC/FP7/283554/">283554</awardNumber>
      <awardTitle>Compositional Operations in Semantic Space</awardTitle>
    </fundingReference>
  </fundingReferences>
</resource>
1,167
736
views
downloads
All versions This version
Views 1,1671,167
Downloads 736736
Data volume 323.6 GB323.6 GB
Unique views 1,0891,089
Unique downloads 285285

Share

Cite as