What Makes a Good Paraphrase: Do Automated Evaluations Work?
Computation and Language
2023-07-28 v1
Abstract
Paraphrasing is the task of expressing an essential idea or meaning in different words. But how different should the words be in order to be considered an acceptable paraphrase? And can we exclusively use automated metrics to evaluate the quality of a paraphrase? We attempt to answer these questions by conducting experiments on a German data set and performing automatic and expert linguistic evaluation.
Cite
@article{arxiv.2307.14818,
title = {What Makes a Good Paraphrase: Do Automated Evaluations Work?},
author = {Anna Moskvina and Bhushan Kotnis and Chris Catacata and Michael Janz and Nasrin Saef},
journal= {arXiv preprint arXiv:2307.14818},
year = {2023}
}
Comments
Extended Abstract for Konvens2023