Automatic analysis of texts from a source language.

摘要

The invention relates to a method for the analysis of source text for an automatic translation of texts, wherein a database is constructed with individual words. Similar words are separated. Each grammatical form is filed as a separate word. Each word receives a number as the first key attribute. The thus constructed dictionary of words with the one-to-one splitting of the vocabulary enables the correct recognition of the source text for translation machines.