What Makes a Good Paraphrase: Do Automated Evaluations Work?

Autor:	Moskvina, Anna, Kotnis, Bhushan, Catacata, Chris, Janz, Michael, Saef, Nasrin
Rok vydání:	2023
Předmět:	Computer Science - Computation and Language
Druh dokumentu:	Working Paper
Popis:	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. Comment: Extended Abstract for Konvens2023
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2307.14818 Zobrazit plný text záznamu View this record from Arxiv