Small Changes Make Big Differences: Improving Multi-turn Response Selection in Dialogue Systems via Fine-Grained Contrastive Learning
Open paper
Benchmark
Model
Rank
Results
conversational-response-selection-on-ubuntu-1
BERT-UMS+FGC
–
R10@1: 0.886
R10@2: 0.948
R10@5: 0.990
Rank counts only results with a code link.