Kalegin Sergei Nikolaevich
Moscow Scientific Research Television Institute
Abstract. The article aims at presenting the current state of the problem of identification of the text language in the form of the review of the known ways of its solutions with the indication of their advantages and disadvantages. Most of these ways can be used either with computers (machine processing) or without them. This review shows clearly the strengths and weaknesses of each method indicating the conditions of its use. Besides, the emphasis is put on the mathematical ways for identifying the linguistic belonging of the text. In conclusion the author proposes his own version of the linguistic identification of the text.
Key words and phrases: способ определения языка, языковая идентификация текста, машинная обработка текста, определение языковой группы текста, языковая принадлежность текста, way of language identification, linguistic identification of the text, machine processing of the text, identification of linguistic group of the text, linguistic belonging of the text
Open the whole article in PDF format. Free PDF-files viewer can be downloaded .
References:
Anisimovich K. V., Tereshchenko V. V., Rybkin V. Yu., Abi Softver. Sposob avtomaticheskogo opredeleniya yazyka raspoznavaemogo teksta pri mnogoyazychnom raspoznavanii: patent № 2251737 RF, G06K9/68 / Ltd. (CY). Opubl. 10.05.2005.
Lapshin V. A., Pshekhotskaya E. A., Perov D. V. Sposob avtomatizirovannogo opredeleniya yazyka i (ili) kodirovki tekstovogo dokumenta: patent № 2500024 RF, G06F17/00 / "Tsentr Innovatsii Natal'i Kasperskoi" (RU). Opubl. 27.11.2013.
Seleznev K. Obrabotka tekstov na estestvennom yazyke [Elektronnyi resurs] // Otkrytye sistemy. 2003. № 12. URL: http://www.osp.ru/os/2003/12/183694/ (data obrashcheniya: 31.10.2015).
Al-Karmi, Abdel Naser, Shamsher S., Baldev Singh. Optical character recognition of handwritten or cursive text in multiple languages (Opticheskoe raspoznavanie simvolov rukopisnogo ili kursivnogo mnogoyazychnogo teksta): patent № 6370269 SShA / International Business Machines Corporation (USA). Opubl. 09.04.2002.
Русский
