Comparing rating scales and preference judgements in language evaluation
- Anja Belz,
- Eric Kow
Research output:
Chapter in Book/Conference proceeding with ISSN or ISBN
Conference contribution with ISSN or ISBN
Research
Peer-reviewAbout the research
Rating-scale evaluations are common in NLP, but are problematic for a range of reasons, e.g. they can be unintuitive for evaluators, inter-evaluator agreement and self-consistency tend to be low, and the parametric statistics commonly applied to the results are not generally considered appropriate for ordinal data. In this paper, we compare rating scales with an alternative evaluation paradigm, preference-strength judgement experiments (PJEs), where evaluators have the simpler task of deciding which of two texts is better in terms of a given quality criterion. We present three pairs of evaluation experiments assessing text fluency and clarity for different data sets, where one of each pair of experiments is a rating-scale experiment, and the other is a PJE. We find the PJE versions of the experiments have better evaluator self-consistency and inter-evaluator agreement, and a larger proportion of variation accounted for by system differences, resulting in a larger number of significant differences being found.
Documents and links
License:Unspecified
Final published version
License:Unspecified
Research output information
Output type
Research output:
Chapter in Book/Conference proceeding with ISSN or ISBN
Conference contribution with ISSN or ISBN
Research
Peer-reviewOriginal language
EnglishPages from-to (Number of pages)
Pages 7-15 (9 pages)Publication milestones
- Published - 01/01/2010
Publication status
Published - 01/01/2010
