Strongly Incremental Constituency Parsing with Graph Neural Networks
Open paper
Benchmark
Model
Rank
Results
constituency-parsing-on-ctb5
Attach-Juxtapose Parser + BERT
#1
F1 score: 93.52
constituency-parsing-on-penn-treebank
Attach-Juxtapose Parser + XLNet
#4
F1 score: 96.34
Rank counts only results with a code link.