Can summarization approximate simplification? A gold standard comparison
This work addresses the lack of cohesion in simplification evaluation by exploring overlaps with summarization, which is incremental for NLP researchers.
The study investigated whether abstractive summarization can approximate text simplification by comparing BART-based BRIO summarization outputs to gold-standard simplifications on the Newsela corpus, achieving a top ROUGE-L score of 0.654.
This study explores the overlap between text summarization and simplification outputs. While summarization evaluation methods are streamlined, simplification lacks cohesion, prompting the question: how closely can abstractive summarization resemble gold-standard simplification? We address this by applying two BART-based BRIO summarization methods to the Newsela corpus, comparing outputs with manually annotated simplifications and achieving a top ROUGE-L score of 0.654. This provides insight into where summarization and simplification outputs converge and differ.