EASIER PROJECT

The EASIER project is being developed by the Human Language and Accessibility Technologies (HULAT) research group (http://hulat.inf.uc3m.es/ )of the Computer Science department of the Universidad Carlos III de Madrid (UC3M). The objective of the project is to develop technological solutions that improve accessibility in access to web content for people with intellectual disabilities, the elderly, and all people in general. It offers a web system with an accessible interface that provides systematic lexical simplification of Spanish texts.

With this goal, a web system is offered (http://easier.hulat.uc3m.es/) that increases cognitive accessibility and provides various language tools. The web system is designed optimizing cognitive accessibility features following easy-to-read, plain language guidelines, as well as WCAG 2.1 (Level AA). This web system can be accessed from the desktop computer or from the mobile. In addition, a browser extension is offered (Chrome and Firefox).

The EASIER system, with its service-oriented architecture, provides a range of resources to improve cognitive accessibility. Complex words are identified within a Spanish text, and different services are offered, such as synonyms, definitions and pictograms, for each complex word. These language services are obtained using Natural Language Processing methods with automatic learning approaches providing a systematic process.

Following a user-centred approach, the project proposal is designed and evaluated considering the collaboration of organizations and associations of people with intellectual disabilities such as Plena Inclusión Madrid and Grupo AMÁS.

This work was supported by the Accessible Technologies award - INDRA Technologies and the Fundación Universia (www.tecnologiasaccesibles.com ), and the Research Program of the Ministry of Economy and Competitiveness - Government of Spain, (DeepEMR project TIN2017-87548-C2-1-R).

Research team:

• Principal investigator: Lourdes Moreno (Lmoreno@inf.uc3m.es )
• Research team: Rodrigo Alarcon, Paloma Martínez, Isabel Segura-Bedmar
• Research Technical Support staff: Jesús Galán Llano, Elena Gonzalez Sabin

Human Language and Accessibility Technologies (HULAT) Group (http://hulat.inf.uc3m.es/ ). Computer Science Department, Universidad Carlos III de Madrid, Madrid, Spain

REFERENCE:

• Rodrigo Alarcón, Lourdes Moreno, Paloma Martínez. (2021). Lexical Simplification System to Improve Web Accessibility. IEEE Access. 9, 58755-58767. 2169-3536. 2021, Abril. 10.1109/ACCESS.2021.3072697. [Computer Science, Information Systems, 3.745, Q1]
• Lourdes Moreno, Rodrigo Alarcon, and Paloma Martínez. 2020. EASIER system. Language resources for cognitive accessibility. In The 22nd International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS ’20), October 26–28, 2020, Virtual Event, Greece. ACM, New York, NY, USA,

Complex Word Identification resources

• Yimam, S. M., Stajner, S., Riedl, M., & Biemann, C. (2017). Multilingual and Cross-Lingual Complex Word Identification. Recent Advances in Natural Language Processing, 813–822. https://doi.org/10.26615/978-954-452-049-6-104
• Cardellino, C. (2016). Spanish {B}illion {W}ords {C}orpus and {E}mbeddings. Retrieved from https://crscardellino.github.io/SBWCE/
• Diccionario de Frecuencias. CORPUS CREA https://www.rae.es/recursos/banco-de-datos/crea

Substitute Generation/Selection resources

• Navigli, R., & Ponzetto, S. (2010). BabelNet: Building a very large multilingual semantic network. Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, (July), 216–225. Retrieved from http://dl.acm.org/citation.cfm?id=1858704
• Pavlick, E., & Callison-Burch, C. (2016). Simple PPDB : A Paraphrase Database for Simplification. (In Proceedings of the 54th ACL), 143–148
• Cardellino, C. (2016). Spanish {B}illion {W}ords {C}orpus and {E}mbeddings. Retrieved from https://crscardellino.github.io/SBWCE/

Word sense disambiguation resources

• J. Devlin, M. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” 2019.
• Natural Language Processing for PyTorch and TensorFlow 2.0 https://github.com/huggingface/transformers

Acknowledgments

• This work is part of the R&D&i ACCESS2MEET (PID2020-116527RB-I0) project financed by MCIN AEI/10.13039/501100011033/, and the "Intelligent and interactive home care system for the mitigation of the COVID-19 pandemic" project (PRTR-REACT UE) awarded by CAM. CONSEJERÍA DE EDUCACIÓN E INVESTIGACION.