RNN-Capsule

Reported on 2 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 Processing2 results

Sentiment AnalysisonMR
Accuracy
83.8
best: 93.3 (VLAWE)
Sentiment AnalysisonSST-5 Fine-grained classification
Accuracy
49.3
best: 62.27 (Llama-3.3-70B + CAPO)