Maximum Bayes Smatch Ensemble Distillation for AMR Parsing

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 experimental setup, we push single model English parser performance to a new state-of-the-art, 85.9 (AMR2.0) and 84.3 (AMR3.0), and return to substantial gains from silver data augmentation. We also attain a new state-of-the-art for cross-lingual AMR parsing for Chinese, German, Italian and Spanish. Finally we explore the impact of the proposed technique on domain adaptation, and show that it can produce gains rivaling those of human annotated data for QALD-9 and achieve a new state-of-the-art for BioAMR.

PDF Abstract NAACL 2022 PDF NAACL 2022 Abstract

Results from the Paper


 Ranked #1 on AMR Parsing on LDC2017T10 (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Benchmark
AMR Parsing LDC2017T10 MBSE Smatch 86.7 # 1
Smatch 85.9 # 3
AMR Parsing LDC2020T02 MBSE Smatch 85.4 # 1
Smatch 84.3 # 4

Methods