Fine-grained text simplification in French: steps towards a better grammaticality - Archive ouverte HAL Access content directly
Conference Papers Year : 2020

Fine-grained text simplification in French: steps towards a better grammaticality

Abstract

The question of easy access to medical and health information by patients has attracted attention of the society and researchers. It has indeed been 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 only address some lexical or syntactic transformations. Besides, little work is done on simplification and adaptation of documents from specialized areas, such as medical and health texts. We propose to combine lexical and syntactic simplification within a rule-based system, and to make the simplification process 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.
Fichier principal
Vignette du fichier
koptient-ISHIMR2020.pdf (111.36 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03095247 , version 1 (04-01-2021)

Identifiers

Cite

Anaïs Koptient, Natalia Grabar. Fine-grained text simplification in French: steps towards a better grammaticality. ISHIMR Proceedings of the 18th International Symposium on Health Information Management Research, Sep 2020, Kalmar, Sweden. ⟨10.15626/ishimr.2020.xxx⟩. ⟨hal-03095247⟩
75 View
83 Download

Altmetric

Share

Gmail Facebook X LinkedIn More