BERT-VFT

Reported on 3 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing3 results

Conversational Response SelectiononUbuntu Dialogue (v1, Ranking)
R10@1· 2019-08-13
0.855
best: 0.918 (Dial-MAE)
An Effective Domain Adaptive Post-Training Method for BERT in Response Selection arXiv:1908.04812
Conversational Response SelectiononUbuntu Dialogue (v1, Ranking)
R10@2· 2019-08-13
0.928
best: 0.965 (BERT-FP+EDHNS)
An Effective Domain Adaptive Post-Training Method for BERT in Response Selection arXiv:1908.04812
Conversational Response SelectiononUbuntu Dialogue (v1, Ranking)
R10@5· 2019-08-13
0.985
best: 0.994 (BERT-FP+EDHNS)
An Effective Domain Adaptive Post-Training Method for BERT in Response Selection arXiv:1908.04812