A Structure Self-Aware Model for Discourse Parsing on Multi-Party Dialogues
Open paper
Benchmark
Model
Rank
Results
discourse-parsing-on-stac
Struct-Aware
#3
Link & Rel F1: 57.3
Link F1: 73.4
discourse-parsing-on-molweni
Struct-Aware
#4
Link & Rel F1: 58.4
Link F1: 81.6
Rank counts only results with a code link.