Multi-task tri-training

Reported on 5 benchmarks across 1 task · 1 paper · 4 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 AnalysisonMulti-Domain Sentiment Dataset
Average· 2018-04-25
79.15
best: 91.74 (UDALM: Unsupervised Domain Adaptation through Language Modeling)
SOTA
Strong Baselines for Neural Semi-supervised Learning under Domain Shift arXiv:1804.09530
Sentiment AnalysisonMulti-Domain Sentiment Dataset
Books· 2018-04-25
74.86
best: 90.63 (UDALM: Unsupervised Domain Adaptation through Language Modeling)
SOTA
Strong Baselines for Neural Semi-supervised Learning under Domain Shift arXiv:1804.09530
Sentiment AnalysisonMulti-Domain Sentiment Dataset
DVD· 2018-04-25
78.14
best: 89.78 (UDALM: Unsupervised Domain Adaptation through Language Modeling)
SOTA
Strong Baselines for Neural Semi-supervised Learning under Domain Shift arXiv:1804.09530
Sentiment AnalysisonMulti-Domain Sentiment Dataset
Electronics· 2018-04-25
81.45
best: 8506 (Distributional Correspondence Indexing)
SOTA
Strong Baselines for Neural Semi-supervised Learning under Domain Shift arXiv:1804.09530
Sentiment AnalysisonMulti-Domain Sentiment Dataset
Kitchen· 2018-04-25
82.14
best: 93.77 (UDALM: Unsupervised Domain Adaptation through Language Modeling)
Strong Baselines for Neural Semi-supervised Learning under Domain Shift arXiv:1804.09530