The purpose of automatic text simplification is to transform technical or difficult to understand texts into a more friendly version. The semantics must be preserved during this transformation. Automatic text simplification can be done at different levels (lexical, syntactic, semantic, stylistic...) and relies on the corresponding knowledge and resources (lexicon, rules...). Our objective is to propose methods and material for the creation of transformation rules from a small set of parallel sentences differentiated by their technicity. We also propose a typology of transformations and quantify them. We work with French-language data related to the medical domain, although we assume that the method can be exploited on texts in any language and from any domain.

L’objectif de la simplification automatique de textes est de transformer un texte technique ou difficile à comprendre en un document plus compréhensible. Le sens doit être préservé lors de cette transformation. La simplification automatique peut être effectuée à plusieurs niveaux (lexical, syntaxique, sémantique, ou encore stylistique) et repose sur des connaissances et ressources correspondantes (lexique, règles, …). Notre objectif consiste à proposer des méthodes et le matériel pour la création de règles de transformation acquis à partir d'un échantillon de paires de phrases parallèles différenciées par leur technicité. Nous proposons également une typologie de transformations et les quantifions. Nous travaillons avec des données en langue française liées au domain médical, même si nous estimons que notre méthode peut s'appliquer à n'importe quelle langue et n'importe quel domaine de spécialité.

The question on easy access to medical and health information by patients has attracted attention of the society and researchers. It has been indeed observed that poor understanding of medical and health information by patients may be harmful for their healthcare process. We assume that simplification and adaptation of technical documents may provide a solution to this situation. While the dedicated guidelines to the simplification summarize different kinds of criteria to consider, actually, it is still difficult to respect all these criteria. Usually, automatic systems for text simplification address some lexical or syntactic transformations. Besides, little work is done on simplification and adaptation of medical and health texts. We propose to combine lexical and syntactic simplification within a rulebased system, and to make it more fine-grained through additional processing. More particularly, we consider transformation of passive sentences into active sentences, and we control the grammatical concordance within sentences. We work with technical medical documents in French. The results are mainly evaluated according to the three measures specifically dedicated to the simplification: semantics, simplicity and grammaticality.

Easy access to medical and health information for children, foreigners and patients is an important issue for the modern society and research. Indeed, misunderstanding of medical and health information by patients may have a negative impact on their healthcare process and health. Even if several simplification guidelines exist, they are difficult to use by medical experts (i.e. lack of time, difficulty to respect the criteria). Existing simplification systems mainly address some lexical or syntactic transformations. We propose to combine lexical and syntactic simplifications within one rule-based system and to make the process fine-grained thanks to a better control of the grammaticality of sentences.