February 10, 2022 Conference paper Open Access

Pantelis Kyriakidis; Despoina Chatzakou; Theodora Tsikrika; Stefanos Vrochidis; Ioannis Kompatsiaris

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">Self attention</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Multihead attention</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Crisis event detection</subfield>
  </datafield>
  <controlfield tag="005">20230112083358.0</controlfield>
  <datafield tag="500" ind1=" " ind2=" ">
    <subfield code="a">This preprint has not undergone peer review (when applicable) or any post-submission improvements or corrections. The Version of Record of this contribution is published in the 44th European Conference on Information Retrieval, and is available online at https://doi.org/10.1007/978-3-030-99739-7_19</subfield>
  </datafield>
  <controlfield tag="001">6036739</controlfield>
  <datafield tag="711" ind1=" " ind2=" ">
    <subfield code="d">10-14 April 2022</subfield>
    <subfield code="g">ECIR'22</subfield>
    <subfield code="a">44th European Conference on Information Retrieval</subfield>
    <subfield code="c">Stavanger, Norway</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Information Technologies Institute, Centre for Research and Technology Hellas</subfield>
    <subfield code="0">(orcid)0000-0002-9564-7100</subfield>
    <subfield code="a">Despoina Chatzakou</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Information Technologies Institute, Centre for Research and Technology Hellas</subfield>
    <subfield code="0">(orcid)0000-0003-4148-9028</subfield>
    <subfield code="a">Theodora Tsikrika</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Information Technologies Institute, Centre for Research and Technology Hellas</subfield>
    <subfield code="0">(orcid)0000-0002-2505-9178</subfield>
    <subfield code="a">Stefanos Vrochidis</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Information Technologies Institute, Centre for Research and Technology Hellas</subfield>
    <subfield code="0">(orcid)0000-0001-6447-9020</subfield>
    <subfield code="a">Ioannis Kompatsiaris</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">372448</subfield>
    <subfield code="z">md5:bdcb24641493d1f4408f17285c5189bd</subfield>
    <subfield code="u">https://zenodo.org/record/6036739/files/Leveraging Transformer Self Attention Encoder.pdf</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="y">Conference website</subfield>
    <subfield code="u">https://ecir2022.org/</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2022-02-10</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire</subfield>
    <subfield code="p">user-aidaproject</subfield>
    <subfield code="o">oai:zenodo.org:6036739</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">Information Technologies Institute, Centre for Research and Technology Hellas</subfield>
    <subfield code="0">(orcid)0000-0002-5963-8776</subfield>
    <subfield code="a">Pantelis Kyriakidis</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Leveraging Transformer Self Attention Encoder for Crisis Event Detection in Short Texts</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-aidaproject</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">883293</subfield>
    <subfield code="a">IMMERSE. INTERACT. INVESTIGATE</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">883596</subfield>
    <subfield code="a">Artificial Intelligence and advanced Data Analytics for Law Enforcement Agencies</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">https://creativecommons.org/licenses/by/2.0/legalcode</subfield>
    <subfield code="a">Creative Commons Attribution 2.0 Generic</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;Analyzing content generated on social media has proven to be a powerful tool for early detection of crisis-related events. Such an analysis may allow for timely action, mitigating or even preventing altogether the effects of a crisis. However, the high noise levels in short texts present in microblogging platforms, combined with the limited publicly available datasets have rendered the task difficult. Here, we propose deep learning models based on a transformer self-attention encoder, which is capable of detecting event-related parts in a text, while also minimizing potential noise levels. Our models efficacy is shown by experimenting with CrisisLexT26, achieving up to 81.6% f1-score and 92.7% AUC.&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.6036738</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.6036739</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">conferencepaper</subfield>
  </datafield>
</record>