A Review of Research-Based Automatic Text Simplification Tools

Proceedings of Recent Advances in Natural Language Processing, pages 321–330 Varna, Sep 4–6, 2023 https://doi.org/10.26615/978-954-452-092-2_036 321 A Review of Research-based Automatic Text Simplification Tools Isabel Espinosa-Zaragoza1, Jos´e Abreu-Salas2, Elena Lloret3, Paloma Moreda3 and Manuel Palomar3 1 Center of Digital Intelligence, University of Alicante isabel.espinosa@ua.es 2 University Institute for Computing Research, University of Alicante ji.abreu@ua.es 3 Department of Computing and Information Systems, University of Alicante {elloret,paloma,mpalomar}@dlsi.ua.es Abstract In the age of knowledge, the democratisation of information facilitated through the Internet may not be as pervasive if written language poses challenges to particular sectors of the popula- tion. The objective of this paper is to present an overview of research-based automatic text simplification tools. Consequently, we describe aspects such as the language, language phenom- ena, language levels simplified, approaches, specific target populations these tools are cre- ated for (e.g. individuals with cognitive impair- ment, attention deficit, elderly people, children, language learners), and accessibility and avail- ability considerations. The review of existing studies covering automatic text simplification tools is undergone by searching two databases: Web of Science and Scopus. The eligibility criteria involve text simplification tools with a scientific background in order to ascertain how they operate. This methodology yielded 27 text simplification tools that are further analysed. Some of the main conclusions reached with this review are the lack of resources accessible to the public, the need for customisation to fos- ter the individual’s independence by allowing the user to select what s/he finds challenging to understand while not limiting the user’s capabil- ities and the need for more simplification tools in languages other than English, to mention a few. 1 Introduction In the age of knowledge and information, the democratisation of information facilitated through the Internet may not be as pervasive owing to poten- tial challenges posed by written language, partic- ularly among specific segments of the population. A great deal of the daily life processes are written and may produce lexical, syntactic and/or semantic difficulties in general, but particularly for those most vulnerable, such as people with cognitive disabilities, autism spectrum disorders, non-native speakers, children, and others. The guidelines pro- vided by organisations like the Plain Language As- sociation International (PLAIN)1 and easy-to-read movement (AENOR, 2018) already highlight both the need for and the promotion of text understand- ability via the simplification of specific language phenomena. Therefore, enhancing text readability and comprehensibility becomes essential to uphold the right to cognitively accessible texts. Currently, these simplification tasks are laborious and time- consuming as they are conducted manually. Thus, Natural Language Processing (NLP) techniques, particularly Automatic Text Simplification (ATS), are demanded by society to address this issue. The objective of this paper is to present the ex- isting tools for ATS, paying particular attention to those whose target audience is a specific group of people with special needs. Consequently, an analy- sis of these tools is conducted to determine the spe- cific languages, language phenomena and linguistic levels they simplify; the approaches followed; their intended target audience (i.e. individuals with cog- nitive …

Content truncated to 500 words