Block-sparse LSTM

Reported on 4 benchmarks across 1 task

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

Natural Language Processing4 results

Sentiment AnalysisonCR
Accuracy
92.2
best: 93.54 (AnglE-LLaMA-7B)
Sentiment AnalysisonSST-2 Binary classification
Accuracy
93.2
best: 97.5 (T5-11B)
Sentiment AnalysisonYelp Binary classification
Error
3.27
best: 1.37 (XLNet)
Sentiment AnalysisonIMDb
Accuracy
94.99
best: 96.68 (RoBERTa-large with LlamBERT)