BiLSTM+CHIM

Reported on 3 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 Processing3 results

Sentiment AnalysisonUser and product information
IMDB (Acc)· 2019-08-26
56.4
best: 57.3 (MA-BERT)
SOTA
Rethinking Attribute Representation and Injection for Sentiment Classification arXiv:1908.09590
Sentiment AnalysisonUser and product information
Yelp 2014 (Acc)· 2019-08-26
69.2
best: 71.4 (MA-BERT)
SOTA
Rethinking Attribute Representation and Injection for Sentiment Classification arXiv:1908.09590
Sentiment AnalysisonUser and product information
Yelp 2013 (Acc)· 2019-08-26
67.8
best: 70.3 (MA-BERT)
Rethinking Attribute Representation and Injection for Sentiment Classification arXiv:1908.09590