@inproceedings{ecf64ef1277a4be0887ee724e06ef31e,
title = "BLEU is not suitable for the evaluation of text simplification",
abstract = "BLEU is widely considered to be an informative metric for text-to-text generation, including Text Simplification (TS). TS includes both lexical and structural aspects. In this paper we show that BLEU is not suitable for the evaluation of sentence splitting, the major structural simplification operation. We manually compiled a sentence splitting gold standard corpus containing multiple structural paraphrases, and performed a correlation analysis with human judgments.1 We find low or no correlation between BLEU and the grammaticality and meaning preservation parameters where sentence splitting is involved. Moreover, BLEU often negatively correlates with simplicity, essentially penalizing simpler sentences.",
author = "Elior Sulem and Omri Abend and Ari Rappoport",
note = "Publisher Copyright: {\textcopyright} 2018 Association for Computational Linguistics; 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018 ; Conference date: 31-10-2018 Through 04-11-2018",
year = "2018",
month = jan,
day = "1",
language = "American English",
series = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018",
pages = "738--744",
editor = "Ellen Riloff and David Chiang and Julia Hockenmaier and Jun'ichi Tsujii",
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018",
}