Co-training an Unsupervised Constituency Parser with Weak Supervision
Open paper
Benchmark
Model
Rank
Results
constituency-grammar-induction-on-ptb
inside-outside co-training + weak supervision
#9
Mean F1 (WSJ): 63.1
Max F1 (WSJ): 66.8
Mean F1 (WSJ10): 74.2
Rank counts only results with a code link.