TEASEL

Reported on 5 benchmarks across 1 task · 1 paper · 3 SOTA

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

Natural Language Processing5 results

Sentiment AnalysisonCMU-MOSI
Acc-2· uses extra data· 2021-09-12
87.5
best: 90.35 (MMML)
SOTA
TEASEL: A Transformer-Based Speech-Prefixed Language Model arXiv:2109.05522
Sentiment AnalysisonCMU-MOSI
Corr· uses extra data· 2021-09-12
0.836
best: 0.8824 (MMML)
SOTA
TEASEL: A Transformer-Based Speech-Prefixed Language Model arXiv:2109.05522
Sentiment AnalysisonCMU-MOSI
MAE· uses extra data· 2021-09-12
0.64
best: 0.5573 (MMML)
SOTA
TEASEL: A Transformer-Based Speech-Prefixed Language Model arXiv:2109.05522
Sentiment AnalysisonCMU-MOSI
Acc-7· uses extra data· 2021-09-12
47.52
best: 52.72 (MMML)
TEASEL: A Transformer-Based Speech-Prefixed Language Model arXiv:2109.05522
Sentiment AnalysisonCMU-MOSI
F1· uses extra data· 2021-09-12
85
best: 90.35 (MMML)
TEASEL: A Transformer-Based Speech-Prefixed Language Model arXiv:2109.05522