Lexical Sensitivity of WSD: An Outlook

Abstract

We have tried to show from our discussion in the previous chapters that while ensembles of classifiers based on supervised learning methods trained on multiple contextual features have proved to perform superiorly in current mainstream automatic word sense disambiguation, and their performance might have apparently reached a plateau, there are still considerable unknowns as far as the lexical sensitivity of the task is concerned. We have also suggested that these under-explored parts cannot be adequately addressed from the computational perspective alone, as they probably involve some intrinsic properties of words and senses, like concept concreteness, which may be cognitively based. In this final chapter, we put forth some preliminary evidence regarding the impact of concept concreteness on the information demand in disambiguation, and conclude with a research agenda which attempts to bring the two camps closer to advance the research on an area of their mutual concern.