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
Datasets
Results from the Paper
Ranked #1 on
AMR Parsing
on LDC2020T02
(using extra training data)
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Uses Extra Training Data |
Benchmark |
|---|---|---|---|---|---|---|---|
| AMR Parsing | Bio | StructBART + MBSE (IBM) | Smatch | 66.9 | # 1 | ||
| AMR Parsing | LDC2017T10 | StructBART + MBSE (IBM) | Smatch | 85.9 | # 4 | ||
| Smatch | 86.7 | # 1 | |||||
| AMR Parsing | LDC2020T02 | Graphene Smatch (MBSE paper) (IBM) | Smatch | 85.4 | # 1 | ||
| AMR Parsing | LDC2020T02 | StructBART + MBSE (IBM) | Smatch | 84.3 | # 5 |
