Abstract EN:

When carrying out the automatic analysis of a text, one of the first stages consists in determining the grammatical categories of the words. In order to do this, a dictionary has been designed which recognises the one or several grammatical categories of non-compound words from their endings. This dictionary, which we have called automatic dictionary, is a collection of general rules (which can consist of sub- rules). A general rule sets forth an ending. An operator (the one or several grammatical categories) is associated with each rule. For example, we have the following general rule: +words ending in 'able' are adjectives;. Examples of exceptions to (or sub-rules) of this general rule are nouns such as (+cartable ;), conjugated verbs like (+ accable ;), and morphological ambiguities such as + noun and conjugated verb (like +sable;, +table. . . ;), and ambiguities such as + adjectival nouns ;(like, for example, + comptable ;. . . ) consequently, this sort of dictionary gives prominence to those words posessing several grammatical categories. When the automatic dictionary detects a word posessing several categories, the grammar system is consulted,of which the role is to pick out the morphological ambiguities by studying the immediate context. The rules in the grammar system work like a group of possible combinations of elements capable of going after and-or before the ambiguous form ( for example, a rule states that an ambiguous form such as + pronoun or article ; preceded by + a cause de ; is, in fact, an article).