Language Identifier: A Computer Program for Automatic Natural-Language Identification of On-line Tex

The rst step in translating any text is to identify the language in which it is written. Several useful methods have already appeared for language identiication where the mystery texts are properly spelled and accented paper documents. Unfortunately, in machine-translation environments, where texts are on-line and may exhibit a variety of conventions for character-mapping and accentuation, the problem is far more diicult. This paper outlines a generalized approach to language identiication of on-line text based on techniques of cryptanalysis. A working prototype has been built, and the results are promising.