Making It Simplext

Abstract

The way in which a text is written can be a barrier for many people. Automatic text simplification is a natural language processing technology that, when mature, could be used to produce texts that are adapted to the specific needs of particular users. Most research in the area of automatic text simplification has dealt with the English language. In this article, we present results from the Simplext project, which is dedicated to automatic text simplification for Spanish. We present a modular system with dedicated procedures for syntactic and lexical simplification that are grounded on the analysis of a corpus manually simplified for people with special needs. We carried out an automatic evaluation of the system’s output, taking into account the interaction between three different modules dedicated to different simplification aspects. One evaluation is based on readability metrics for Spanish and shows that the system is able to reduce the lexical and syntactic complexity of the texts. We also show, by means of a human evaluation, that sentence meaning is preserved in most cases. Our results, even if our work represents the first automatic text simplification system for Spanish that addresses different linguistic aspects, are comparable to the state of the art in English Automatic Text Simplification.

Adaptação Lexical Automática em Textos Informativos do Português Brasileiro para o Ensino Fundamental

“…Essa abordagem também obteve resultados superiores a baselines que utilizavam apenas conhecimento lexical, selecionando o sinônimo mais frequente do OpenThesaurus como substituto. LexSiS foi incorporado no sistema Simplext (Saggion et al, 2015), que trata também a Simplificação Sintática para o espanhol, eé composto por três módulos: o módulo de Simplificação Sintática, o módulo LexSiS, que faz a Simplificação Lexical baseada em sinônimos, e um módulo de Simplificação Lexical baseado em regras que cobre simplificações não resolvidas pelos módulos anteriores como normalização de verbos de elocução, redução do conteúdo de sentenças, e redução, explicação ou normalização de informação numérica. Kajiwara et al (2013) desenvolveram um trabalho em Simplificação Lexical para o Japonês.…”

Automatic Definition Extraction and Crossword Generation From Spanish News Text

“…We first process the corpus with the FreeLing POS-tagger [20], which also performs a named entity recognition and classification task, and with the clause analyzer 2 ClaTex [21]. Then we search for clauses which may contain definitions by applying the lexical pattern.…”

Perspectives on Speech and Language Interaction for Daily Assistive Technology

“…In the first two cases, this involves modifying atypical speech to be more understandable to nonfamiliar listeners [Mcloughlin et al 2015;Aihara et al 2015]. In the third, the aim was to make text more intelligible to readers with low literacy skills [Saggion et al 2015]. In all these articles, an important part of the study is devoted to the experimentation with real users in realistic settings to measure the effectiveness of the proposed method and to identify important challenges to overcome.…”