ConvBERT-DG

Reported on 8 benchmarks across 1 task

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

Natural Language Processing8 results

Natural Language UnderstandingonDialoGLUE fewshot
Average
74.6
Natural Language UnderstandingonDialoGLUE fewshot
Banking77 (Acc)
84.84
best: 88.99 (BanLanGen)
Natural Language UnderstandingonDialoGLUE fewshot
CLINC150 (Acc)
93.53
best: 95.64 (BanLanGen)
Natural Language UnderstandingonDialoGLUE fewshot
DSTC8 (F-1)
46.63
best: 56.88 (mslm)
Natural Language UnderstandingonDialoGLUE fewshot
HWU64 (Acc)
86.71
best: 93.06 (ConvBERT-DG + Pre + Multi)
Natural Language UnderstandingonDialoGLUE fewshot
MultiWOZ (Joint Goal Acc)
49.59
Natural Language UnderstandingonDialoGLUE fewshot
Restaurant8k (F-1)
87.33
best: 87.58 (ConvBERT-DG + Pre + Multi)
Natural Language UnderstandingonDialoGLUE fewshot
TOP (EM)
73.56
best: 78.84 (ConvBERT + Pre + Multi)