1 code implementation • Findings (ACL) 2022 • Brodie Mather, Bonnie J Dorr, Adam Dalton, William de Beaumont, Owen Rambow, Sonja M. Schmer-Galunder
We develop a ground truth (GT) based on expert annotators and compare our concern detection output to GT, to yield 231% improvement in recall over baseline, with only a 10% loss in precision.