Computerizing a machine readable dictionary

摘要: Current research in natural language processing is characterized by the development of theories grammar which strongly depend on lexicon to drive parsing systems (e.g. Lexical Function Grammar, General Phrase Structured Functional Unification Grammar). These requirements go far beyond typical small, hand-coded vocabularies developed for theoretical or demonstration purposes. Many researchers have independently discovered rich, though unstructured, knowledge sources that machine readable dictionaries offer. This paper reports an attempt impose structure Funk and Wagnalls Dictionary, means a parser written Turbo Pascal, using mixed approach pattern matching transition networks. The resulting computerized dictionary 95 % accurate, but correcting final 5% incorrectly parsed involves painstakingly scrutinizing output modifying handle exceptional cases occur only once twice entire MRD, editing remove errors introduced OCR process.