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 extended seamlessly to exploit structured knowledge from semantic networks to achieve state-of-the-art results in English all-words WSD.
Framing word sense disambiguation as a multi-label problem for model-agnostic knowledge integration / Conia, S.; Navigli, R.. - (2021), pp. 3269-3275. (Intervento presentato al convegno 16th Conference of the European Chapter of the Associationfor Computational Linguistics, EACL 2021 tenutosi a Online) [10.18653/v1/2021.eacl-main.286].
Framing word sense disambiguation as a multi-label problem for model-agnostic knowledge integration
Conia S.
Primo
;Navigli R.
Ultimo
2021
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 extended seamlessly to exploit structured knowledge from semantic networks to achieve state-of-the-art results in English all-words WSD.File | Dimensione | Formato | |
---|---|---|---|
Conia_Framing-Word_2021.pdf
accesso aperto
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Creative commons
Dimensione
707.9 kB
Formato
Adobe PDF
|
707.9 kB | Adobe PDF |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.