FIELD: information technology.
SUBSTANCE: device that converts free text sources into the morpheme database and free language words with search capability, contains: one or more processors; one or more memory devices; as well as the hierarchically arrangement, stored in one or more memory devices, each entry in which corresponds to the morpheme, word or phrase, represented as the sequence of nonparameterized symbols, that reproduce the language-specific elements, as well as the program, that provides the extraction of morphemes and words from text sources in one of the free languages for each extracted morpheme or word, converting and storing of the nonparameterized symbols in one or more memory devices, and storing the sequence of nonparametrized symbols in the hierarchically arrangement.
EFFECT: improvement of the printed documents conversion accuracy, which contains the arabic text and the other languages text.
20 cl, 72 dwg
