BiBL: AMR Parsing and Generation with Bidirectional Bayesian Learning

Open paper
Benchmark Model Rank Results
amr-parsing-on-ldc2017t10BiBL+Silver#11Smatch: 84.7
amr-parsing-on-ldc2017t10BiBL#12Smatch: 84.6
amr-parsing-on-ldc2020t02BiBL#8Smatch: 83.9
amr-parsing-on-ldc2020t02BiBL+Silver#9Smatch: 83.5

Rank counts only results with a code link.