January 1, 2021 Conference paper Open Access

Simone Conia; Roberto Navigli

Citation Style Language JSON Export

{
  "DOI": "10.18653/v1/2021.eacl-main.286", 
  "abstract": "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.", 
  "author": [
    {
      "family": "Simone Conia"
    }, 
    {
      "family": "Roberto Navigli"
    }
  ], 
  "id": "115335", 
  "issued": {
    "date-parts": [
      [
        2021, 
        1, 
        1
      ]
    ]
  }, 
  "language": "und", 
  "note": "", 
  "title": "Framing Word Sense Disambiguation as a Multi-Label Problem for Model-Agnostic Knowledge Integration", 
  "type": "paper-conference"
}