Motivated by recent findings on the probabilistic modeling of acceptability judgments, we propose syntactic log-odds ratio (SLOR), a normalized language model score, as a metric for referenceless fluency evaluation of natural language generation output at the sentence level. We further introduce WPSLOR, a novel WordPiece-based version, which harnesses a more compact language model. Even though word-overlap metrics like ROUGE are computed with the help of hand-written references, our referenceless methods obtain a significantly higher correlation with human fluency scores on a benchmark dataset of compressed sentences. Finally, we present ROUGE-LM, a reference-based metric which is a natural extension of WPSLOR to the case of available references. We show that ROUGE-LM yields a significantly higher correlation with human judgments than all baseline metrics, including WPSLOR on its own.
@article{arxiv.1809.08731,
title = {Sentence-Level Fluency Evaluation: References Help, But Can Be Spared!},
author = {Katharina Kann and Sascha Rothe and Katja Filippova},
journal= {arXiv preprint arXiv:1809.08731},
year = {2018}
}