Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Huang, Yichen, Kochmar, Ekaterina
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2403.17640
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910384354492416
author Huang, Yichen
Kochmar, Ekaterina
author_facet Huang, Yichen
Kochmar, Ekaterina
contents Text simplification lacks a universal standard of quality, and annotated reference simplifications are scarce and costly. We propose to alleviate such limitations by introducing REFeREE, a reference-free model-based metric with a 3-stage curriculum. REFeREE leverages an arbitrarily scalable pretraining stage and can be applied to any quality standard as long as a small number of human annotations are available. Our experiments show that our metric outperforms existing reference-based metrics in predicting overall ratings and reaches competitive and consistent performance in predicting specific ratings while requiring no reference simplifications at inference time.
format Preprint
id arxiv_https___arxiv_org_abs_2403_17640
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle REFeREE: A REference-FREE Model-Based Metric for Text Simplification
Huang, Yichen
Kochmar, Ekaterina
Computation and Language
Text simplification lacks a universal standard of quality, and annotated reference simplifications are scarce and costly. We propose to alleviate such limitations by introducing REFeREE, a reference-free model-based metric with a 3-stage curriculum. REFeREE leverages an arbitrarily scalable pretraining stage and can be applied to any quality standard as long as a small number of human annotations are available. Our experiments show that our metric outperforms existing reference-based metrics in predicting overall ratings and reaches competitive and consistent performance in predicting specific ratings while requiring no reference simplifications at inference time.
title REFeREE: A REference-FREE Model-Based Metric for Text Simplification
topic Computation and Language
url https://arxiv.org/abs/2403.17640