WebNLG Challenge: Human Evaluation Results
Abstract
This report presents the human evaluation results for the WebNLG Challenge which was held in 2017. The automatic evaluation results can be found
in [Gardent et al., 2017a]. In this report, we describe human evaluation design, communicate the results, and explore correlation between automatic
and human assessments.
Domains
Computation and Language [cs.CL]
Origin : Files produced by the author(s)