Subcategorization Acquisition as an Evaluation Method for WSD
Proceedings of the Third International Conference on Language Resources and Evaluation (LREC 2002)
Abstract
Evaluation of word sense disambiguation (WSD) systems is often based on machine-readable dictionaries (MRDs). Such evaluation typically employs a set of fine-grained dictionary senses and considers them all to be equally important. In this paper, we propose a novel evaluation method for WSD systems in the context of automatic subcategorization acquisition. Building on an extant subcategorization acquisition system, we show that the system would benefit from WSD and propose modifications which allow it to make use of WSD. The enhanced subcategorization acquisition system can then be used as a task-based evaluation method for WSD systems where both the notion of sense and the sense's relevance to the evaluation process is determined by the application itself.