Maximum Bayes Smatch Ensemble Distillation for AMR Parsing. (arXiv:2112.07790v2 [cs.CL] UPDATED)

AMR parsing has experienced an unprecendented increase in performance in the
last three years, due to a mixture of effects including architecture
improvements and transfer learning. Self-learning techniques have also played a
role in pushing performance forward. However, for most recent high performant
parsers, the effect of self-learning and silver data augmentation seems to be
fading. In this paper we propose to overcome this diminishing returns of silver
data by combining Smatch-based ensembling techniques with ensemble
distillation. In an extensive …

amr arxiv bayes distillation ensemble parsing