Sampling Matters! An Empirical Study of Negative Sampling Strategies for Learning of Matching Models in Retrieval-based Dialogue Systems
Open paper
Benchmark
Model
Rank
Results
conversational-response-selection-on-ubuntu-1
DAM-Semi
–
R10@1: 0.785
R10@2: 0.883
R10@5: 0.974
R2@1: 0.944
Rank counts only results with a code link.