The increasing number of international and epidemiological studies of Alzheimer's disease points to the need for linguistically equivalent translations of measures for identifying the presence, types, and severity of dementia in cross-cultural populations. In translating the CERAD (Consortium to Establish a Registry for Alzheimer's Disease) neuropsychological instruments into French, several linguistic issues have emerged such as semantic, phonetic, and word-frequency equivalences. In verbal memory tests, these problems, though minor in appearance, can be major pitfalls in studies comparing cognitive function in populations differing in language. Description of the translation procedure and examples of problems encountered are presented, with measures taken to resolve them.