Is human scoring the best criteria for summary evaluation?

Findings (ACL) 2021  ·  Oleg Vasilyev, John Bohannon ·

Normally, summary quality measures are compared with quality scores produced by human annotators. A higher correlation with human scores is considered to be a fair indicator of a better measure. We discuss observations that cast doubt on this view. We attempt to show a possibility of an alternative indicator. Given a family of measures, we explore a criterion of selecting the best measure not relying on correlations with human scores. Our observations for the BLANC family of measures suggest that the criterion is universal across very different styles of summaries.

PDF Abstract Findings (ACL) 2021 PDF Findings (ACL) 2021 Abstract


  Add Datasets introduced or used in this paper

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.