MACHINE READABLE DICTIONARIES: WHAT HAVE WE LEARNED, WHERE DO WE GO?
Nancy Ide, Jean Véronis, Robert Schuman · 1999
Machine-readable versions of everyday dictionaries have been seen as a likely source of information for use in natural language processing because they contain an enormous amount of lexical and semantic knowledge. However, after fifteen years of research, the results appear to be disappointing. No comprehensive evaluation of machine-readable dictionaries (MRDs) as a knowledge source has been made to date, although this is necessary to determine what, if anything, can be gained from MRD research. To this end, this paper provides an overview and assessment of MRD research to date. It then proposes possible future directions and applications that may exploit these years of effort, in the light of current directions in not only NLP research, but also fields such as lexicography and electronic publishing. 1. Introduction The need for robust lexical and semantic information to assist in realistic natural language processing (NLP) applications is well known. Machine-readable dictionaries (MR...