English

Sentence-Level Fluency Evaluation: References Help, But Can Be Spared!

Computation and Language 2018-09-25 v1

Abstract

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.

Keywords

Cite

@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}
}

Comments

Accepted to CoNLL 2018

R2 v1 2026-06-23T04:15:45.558Z