ИСТИНА

ABSTRACT The linguistic methods providing grammatical and lexical control of the acoustic recognition results are described. The parser (NL-Processor) uses original local grammar, ATN-type grammar, and comprehensive computer dictionaries of grammatical words, collocations, and pattern of government for verbs. The parsing is applied to "word garlands", i.e. to more complex object than word strings that are the object of processing with the prior parsing techniques. To choose the best of the plausible strings a special meta-level is introduced that deals with the multi-criterion choice problem. An important distinctive feature of the solution of this problem by the techniques employed is that the best string does not necessarily have to be a grammatical one. KEY WORDS Grammar, Grammatical dictionary, Knowledge base, Parsing, Speech recognition.