Learning an Effective Context-Response Matching Model with Self-Supervised Tasks for Retrieval-based Dialogues

Benchmark Model Rank Results
conversational-response-selection-on-eBERT-SLR10@1: 0.776R10@2: 0.919R10@5: 0.991
conversational-response-selection-on-ubuntu-1BERT-SLR10@1: 0.884R10@2: 0.946R10@5: 0.990R2@1: 0.975