Zenodo.org will be unavailable for 2 hours on September 29th from 06:00-08:00 UTC. See announcement.

Conference paper Open Access

Elastic Embedded Background Linking for News Articles with Keywords, Entities and Events

Cabrera-Diego, Luis Adrián; Boros, Emanuela; Doucet, Antoine


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nam##2200000uu#4500</leader>
  <datafield tag="041" ind1=" " ind2=" ">
    <subfield code="a">eng</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Information system, Language models, Rank aggregation</subfield>
  </datafield>
  <controlfield tag="005">20220308014900.0</controlfield>
  <controlfield tag="001">6334523</controlfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of La Rochelle</subfield>
    <subfield code="a">Boros, Emanuela</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of La Rochelle</subfield>
    <subfield code="a">Doucet, Antoine</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">341874</subfield>
    <subfield code="z">md5:1de7b096e8662eb7ac28508442b19bbd</subfield>
    <subfield code="u">https://zenodo.org/record/6334523/files/TREC_News_2021.pdf</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2022-03-07</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire</subfield>
    <subfield code="p">user-newseye</subfield>
    <subfield code="o">oai:zenodo.org:6334523</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">University of La Rochelle</subfield>
    <subfield code="a">Cabrera-Diego, Luis Adrián</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Elastic Embedded Background Linking for News Articles with Keywords, Entities and Events</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-newseye</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">770299</subfield>
    <subfield code="a">NewsEye: A Digital Investigator for Historical Newspapers</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">https://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;In this paper, we present a collection of five flexible background linking models created for the News Track in TREC 2021 that generate ranked lists of articles to provide contextual information. The collection is based on the use of sentence embeddings indexes, created with Sentence BERT and Open Distro for ElasticSearch. For each model, we explore additional tools, from keywords extraction using YAKE, to entity and event detection, while passing through a linear combination. The associated code is available online as open-source software.&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.6334522</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.6334523</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">conferencepaper</subfield>
  </datafield>
</record>
141
71
views
downloads
All versions This version
Views 141141
Downloads 7171
Data volume 24.3 MB24.3 MB
Unique views 130130
Unique downloads 6767

Share

Cite as