Sense abstractness, semantic activation, and word sense disambiguation

Concrete concepts are often easier to understand than abstract concepts. The notion of abstractness is thus closely tied to the organisation of our semantic memory, and more specifically our internal lexicon, which underlies our word sense disambiguation (WSD) mechanisms. State-of-the-art automatic WSD systems often draw on a variety of contextual cues and assign word senses by an optimal combination of statistical classifiers. The validity of various lexico-semantic resources as models of our internal lexicon and the cognitive aspects pertinent to the lexical sensitivity of WSD are seldom questioned. We attempt to address these issues by examining psychological evidence of the internal lexicon and its compatibility with the information available from computational lexicons. In particular, we compare the responses from a word association task against existing lexical resources, WordNet and SUMO, to explore the relation between sense abstractness and semantic activation, and thus the implications on semantic network models and the lexical sensitivity of WSD. Our results suggest that concrete senses are more readily activated than abstract senses, and broad associations are more easily triggered than narrow paradigmatic associations. The results are expected to inform the construction of lexico-semantic resources and WSD strategies.