Lexical simplification approach using easy-to-read resources

Abstract

This work aims to facilitate the understanding and readability of Spanish texts in a generic domain through the design of a lexical simplification system that provides support to the task of Complex Word Identification (CWI) and selection of a simpler substitute. Considering the limited resources available in Spanish, we explore different features that allow us to discern between a complex word and a simpler one. Some of these features are obtained from easy-to-read resources. The evaluation shows good results by obtaining an F1-Score of 0.7497 on the CWI Task with the BEA Workshop 2018 competition’s dataset.