Paper: Choosing Sense Distinctions for WSD: Psycholinguistic Evidence

ACL ID P08-2063
Title Choosing Sense Distinctions for WSD: Psycholinguistic Evidence
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2008

Supervised word sense disambiguation re- quires training corpora that have been tagged with word senses, which begs the question of which word senses to tag with. The default choice has been WordNet, with its broad cov- erage and easy accessibility. However, con- cerns have been raised about the appropriateness of its fine-grained word senses for WSD. WSD systems have been far more successful in distinguishing coarse- grained senses than fine-grained ones (Navig- li, 2006), but does that approach neglect ne- cessary meaning differences? Recent psycholinguistic evidence seems to indicate that closely related word senses may be represented in the mental lexicon much like a single sense, whereas distantly related senses may be represented more like discrete entities. These result...