Italian Lexical Simplification Benchmark

The corpus is a manually created benchmark to evaluate the performance of Italian lexical simplification systems. It contains 901 pairs of complex sentences and their simplified version at the lexical level (i.e. replacement of a difficult term or phrase with a simpler synonym). The dataset and a system using the benchmark are described in the paper "The impact of phrases on Italian lexical simplification"  https://zenodo.org/record/1048874