Asymmetric tri-training

Reported on 5 benchmarks across 1 task · 1 paper · 2 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· 2017-02-27
78.39
best: 91.74 (UDALM: Unsupervised Domain Adaptation through Language Modeling)
SOTA
Asymmetric Tri-training for Unsupervised Domain Adaptation arXiv:1702.08400
Sentiment AnalysisonMulti-Domain Sentiment Dataset
Kitchen· 2017-02-27
83.97
best: 93.77 (UDALM: Unsupervised Domain Adaptation through Language Modeling)
SOTA
Asymmetric Tri-training for Unsupervised Domain Adaptation arXiv:1702.08400
Sentiment AnalysisonMulti-Domain Sentiment Dataset
Books· 2017-02-27
72.97
best: 90.63 (UDALM: Unsupervised Domain Adaptation through Language Modeling)
Asymmetric Tri-training for Unsupervised Domain Adaptation arXiv:1702.08400
Sentiment AnalysisonMulti-Domain Sentiment Dataset
DVD· 2017-02-27
76.17
best: 89.78 (UDALM: Unsupervised Domain Adaptation through Language Modeling)
Asymmetric Tri-training for Unsupervised Domain Adaptation arXiv:1702.08400
Sentiment AnalysisonMulti-Domain Sentiment Dataset
Electronics· 2017-02-27
80.47
best: 8506 (Distributional Correspondence Indexing)
Asymmetric Tri-training for Unsupervised Domain Adaptation arXiv:1702.08400