Simplicity Level Estimate (SLE): A Learned Reference-Less Metric for Sentence Simplification

Autor:	Cripwell, Liam, Legrand, Joël, Gardent, Claire
Rok vydání:	2023
Předmět:	Computer Science - Computation and Language
Druh dokumentu:	Working Paper
Popis:	Automatic evaluation for sentence simplification remains a challenging problem. Most popular evaluation metrics require multiple high-quality references -- something not readily available for simplification -- which makes it difficult to test performance on unseen domains. Furthermore, most existing metrics conflate simplicity with correlated attributes such as fluency or meaning preservation. We propose a new learned evaluation metric (SLE) which focuses on simplicity, outperforming almost all existing metrics in terms of correlation with human judgements. Comment: Accepted to EMNLP 2023 (Main Conference)
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2310.08170 Zobrazit plný text záznamu View this record from Arxiv