Structural Optimization Ambiguity and Simplicity Bias in Unsupervised Neural Grammar Induction
Open paper
Benchmark
Model
Rank
Results
constituency-grammar-induction-on-ptb
Parse-Focused (NT=4500)
#2
Mean F1 (WSJ): 69.6
Max F1 (WSJ): 70.3
constituency-grammar-induction-on-ptb
Parse-Focused (NT=30)
#3
Mean F1 (WSJ): 67.4
Max F1 (WSJ): 68.4
Rank counts only results with a code link.