Extract-Classify-ACOS

Reported on 6 benchmarks across 3 tasks

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

Natural Language Processing6 results

Sentiment AnalysisonRestaurant-ACOS
F1
44.61
best: 53.45 (BART-ABSA)
Sentiment AnalysisonLaptop-ACOS
F1
35.8
best: 39.41 (BART-ABSA)
Aspect-Based Sentiment Analysis (ABSA)onRestaurant-ACOS
F1
44.61
best: 53.45 (BART-ABSA)
Aspect-Based Sentiment Analysis (ABSA)onLaptop-ACOS
F1
35.8
best: 39.41 (BART-ABSA)
Aspect-Category-Opinion-Sentiment Quadruple ExtractiononRestaurant-ACOS
F1
44.61
best: 53.45 (BART-ABSA)
Aspect-Category-Opinion-Sentiment Quadruple ExtractiononLaptop-ACOS
F1
35.8
best: 39.41 (BART-ABSA)