RACL-BERT

Reported on 8 benchmarks across 2 tasks

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

Natural Language Processing9 results

Sentiment AnalysisonSemEval 2014 Task 4 Subtask 1+2
F1
63.4
best: 83.76 (gpt-3.5 finetuned)
Sentiment AnalysisonSemEval 2014 Task 4 Subtask 1+2
F1
63.4
best: 83.76 (gpt-3.5 finetuned)
Sentiment AnalysisonSemEval 2014 Task 4 Laptop
F1
63.4
best: 79.34 (InstructABSA)
Sentiment AnalysisonSemEval
Avg F1
68.29
best: 76.73 (FS-ABSA)
Sentiment AnalysisonSemEval
Laptop 2014 (F1)
63.4
best: 71.16 (FS-ABSA)
Sentiment AnalysisonSemEval
Restaurant 2014 (F1)
75.42
best: 82.29 (FS-ABSA)
Sentiment AnalysisonSemEval
Restaurant 2015 (F1)
66.05
best: 66.61 (BARTABSA)
Aspect-Based Sentiment Analysis (ABSA)onSemEval 2014 Task 4 Subtask 1+2
F1
63.4
best: 83.76 (gpt-3.5 finetuned)
Aspect-Based Sentiment Analysis (ABSA)onSemEval 2014 Task 4 Laptop
F1
63.4
best: 79.34 (InstructABSA)