BLEU is Not Suitable for the Evaluation of Text Simplification

Elior Sulem, Omri Abend, Ari Rappoport
2018 Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing  
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
more » ... 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.
doi:10.18653/v1/d18-1081 dblp:conf/emnlp/SulemAR18 fatcat:2bavglf6e5bfrdroblf6tse4ru