Automatic Control of Simple Language in Web Pages

Abstract

Abstract. The use of simple and easy to understand language is an essential requirement for web documents to be accessible by people with cognitive or reading disabilities. We present an architecture that scores the readability of textual content automatically and also provides hints about possible obstacles to readability in the given text. Our approach is based on a natural language processing framework that supports all levels of linguistic analysis, ranging from the morphological analysis of words to the semantic analysis of sentences and texts.