A “NATURAL ” LEXICALIZATION MODEL FOR LANGUAGE GENERATION

We propose a general lexicalization model which accounts for how lexical units are selected and introduced in linguistic utterances during language generation. This model aims at “natural-ness ” by being based on actual lexical knowledge used in speech; consequently, it should be com-patible with standard patterns of behavior shown by humans when they speak (flexibility in computing both content and form of linguistic utterances, prototypical types of mistakes and back-tracking, etc.). The main advantage of our model, once implemented in automatic language genera-tion, is that it takes into account fundamental differences that exist between lexical units, with regard to why and how they are used in texts. This is achieved by means of a stratificational approach to lexicalization, where each type of lexical unit is introduced at a proper level of repre-sentation, according to the role it plays in the enunciation. Section 1 offers a general characterization of the approach and makes explicit its main assump-tions. Sections 2 to 4 successively examine the three levels of transition implied by the stratifica-tional structuring of the model. Section 5 concludes with an examination of its relevance to the design of text generation systems. Keywords