Using Relevant Domains Resource for Word Sense Disambiguation.
Sonia Vázquez, Andrés Montoyo, Germán Rigau · 2004
This paper presents a new method for Word Sense Disambiguation based on the WordNet Domains lexical resource [4]. The underlaying working hypothesis is that domain labels, such as ARCHITECTURE, SPORT and MEDICINE provide a natural way to establish semantic relations between word senses, that can be used during the disambiguation process. This resource has already been used on Word Sense Disambiguation [5], but it has not made use of glosses information. Thus, we present in first place, a new lexical resource based on WordNet Domains glosses information, named “Relevant Domains”. In second place, we describe a new method for WSD based on this new lexical resource (“Relevant Domains”). And finally, we evaluate the new method with English allwords task of SENSEVAL2, obtaining promising results.