January 1, 2021 Conference paper Open Access

Simone Conia; Roberto Navigli

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="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">conferencepaper</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">Recent studies treat Word Sense Disambiguation (WSD) as a single-label classification problem in which one is asked to choose only the best-fitting sense for a target word, given its context. However, gold data labelled by expert annotators suggest that maximizing the probability of a single sense may not be the most suitable training objective for WSD, especially if the sense inventory of choice is fine-grained. In this paper, we approach WSD as a multi-label classification problem in which multiple senses can be assigned to each target word. Not only does our simple method bear a closer resemblance to how human annotators disambiguate text, but it can also be seamlessly extended to exploit structured knowledge from semantic networks to achieve state-of-the-art results in English all-words WSD.</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="a">Roberto Navigli</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.18653/v1/2021.eacl-main.286</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <controlfield tag="001">115335</controlfield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2">opendefinition.org</subfield>
  </datafield>
  <controlfield tag="005">20230927015026.0</controlfield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="041" ind1=" " ind2=" ">
    <subfield code="a">und</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-itmirror</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">H2020</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">EC</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">European Research Council</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Consolidator Grant</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">European Commission</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Knowmad Institut</subfield>
  </datafield>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Digital Humanities and Cultural Heritage</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Framing Word Sense Disambiguation as a Multi-Label Problem for Model-Agnostic Knowledge Integration</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="a">Simone Conia</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="a">Other (Open)</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2021-01-01</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">724889</subfield>
    <subfield code="u">https://www.openaccessrepository.it/record/115335/files/fulltext.pdf</subfield>
    <subfield code="z">md5:47e6fbc0812a3b25edafe161c5f9185d</subfield>
  </datafield>
</record>