ULMFiT (pre-trained vocab)

Reported on 4 benchmarks across 2 tasks

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

Natural Language Processing2 results

Text ClassificationonDODF Data
Average F1
0.8374
best: 0.8918 (ULMFiT (pre-trained vocab, no gradual unfreezing))
Text ClassificationonDODF Data
Weighted F1
0.9088
best: 0.9257 (ULMFiT (pre-trained vocab, no gradual unfreezing))

Methodology2 results

ClassificationonDODF Data
Average F1
0.8374
best: 0.8918 (ULMFiT (pre-trained vocab, no gradual unfreezing))
ClassificationonDODF Data
Weighted F1
0.9088
best: 0.9257 (ULMFiT (pre-trained vocab, no gradual unfreezing))