A Linear-Time Bottom-Up Discourse Parser with Constraints and Post-Editing
Open paper
Benchmark
Model
Rank
Results
discourse-parsing-on-rst-dt
Bottom-up Linear-chain CRF-based Parser
–
RST-Parseval (Span): 85.7
RST-Parseval (Nuclearity): 71.0
…
Rank counts only results with a code link.