January 1, 2021 Conference paper Open Access

Simone Conia; Roberto Navigli

Dublin Core Export

<?xml version='1.0' encoding='utf-8'?>
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
  <dc:creator>Simone Conia</dc:creator>
  <dc:creator>Roberto Navigli</dc:creator>
  <dc:date>2021-01-01</dc:date>
  <dc:description>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.</dc:description>
  <dc:identifier>https://www.openaccessrepository.it/record/115335</dc:identifier>
  <dc:identifier>10.18653/v1/2021.eacl-main.286</dc:identifier>
  <dc:language>und</dc:language>
  <dc:relation>url:https://www.openaccessrepository.it/communities/itmirror</dc:relation>
  <dc:rights>info:eu-repo/semantics/openAccess</dc:rights>
  <dc:subject>H2020</dc:subject>
  <dc:subject>EC</dc:subject>
  <dc:subject>European Research Council</dc:subject>
  <dc:subject>Consolidator Grant</dc:subject>
  <dc:subject>European Commission</dc:subject>
  <dc:subject>Knowmad Institut</dc:subject>
  <dc:subject>Digital Humanities and Cultural Heritage</dc:subject>
  <dc:title>Framing Word Sense Disambiguation as a Multi-Label Problem for Model-Agnostic Knowledge Integration</dc:title>
  <dc:type>info:eu-repo/semantics/conferencePaper</dc:type>
  <dc:type>publication-conferencepaper</dc:type>
</oai_dc:dc>