UnifiedABSA (multi-task)

Reported on 4 benchmarks across 2 tasks · 1 paper

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

Natural Language Processing4 results

Sentiment AnalysisonACOS
F1 (Laptop)· uses extra data· 2022-11-20
42.58
best: 43.92 (MvP)
UnifiedABSA: A Unified ABSA Framework Based on Multi-task Instruction Tuning arXiv:2211.10986
Sentiment AnalysisonACOS
F1 (Restaurant)· uses extra data· 2022-11-20
60.6
best: 61.54 (MvP)
UnifiedABSA: A Unified ABSA Framework Based on Multi-task Instruction Tuning arXiv:2211.10986
Aspect-Based Sentiment Analysis (ABSA)onACOS
F1 (Laptop)· uses extra data· 2022-11-20
42.58
best: 43.92 (MvP)
UnifiedABSA: A Unified ABSA Framework Based on Multi-task Instruction Tuning arXiv:2211.10986
Aspect-Based Sentiment Analysis (ABSA)onACOS
F1 (Restaurant)· uses extra data· 2022-11-20
60.6
best: 61.54 (MvP)
UnifiedABSA: A Unified ABSA Framework Based on Multi-task Instruction Tuning arXiv:2211.10986