List your company

Aspect-level Sentiment Analysis on Laptop (test)

86.68AccuracyFlan-T5 + RVISAg
67.4472.43577.4382.425Nov 16, 2018Oct 24, 2019Oct 1, 2020Sep 8, 2021Aug 17, 2022Jul 25, 2023Jul 2, 2024

Evaluation results

MethodLinks
Flan-T5 + RVISAgModel Parameters=11B, Rationale=GPT-3.52024.0786.6884.05
Flan-T5 + RVISAvModel Parameters=11B, Rationale=Vicuna2024.0786.5283.28
BERT Asp + SCAPTModel Parameters=110M2024.0782.7679.15
T5 Base + ABSA-ESAModel Parameters=220M2024.0782.4479.34
Flan-T5 + THORModel Parameters=11B2024.0782.2978.78
Flan-T5 + promptModel Parameters=250M2024.0781.9877.93
Flan-T5 + promptModel Parameters=11B2024.0781.8277.69
BERT Asp + CEPTModel Parameters=110M2024.0781.6678.38
Flan-T5 + THORModel Parameters=250M2024.0781.6677.51
Flan-T5 + RVISAgModel Parameters=250M, Rationale=GPT-3.52024.0781.1977.13
Flan-T5 + RVISAvModel Parameters=250M, Rationale=Vicuna2024.0780.7276.49
BERT + ADA+Model Parameters=110M2024.0778.9674.18
BERT + SPC+Model Parameters=110M2024.0778.2273.45
BERT + RGATModel Parameters=110M2024.0778.2174.07
MGANModel=Full Model2018.1176.2171.42
MGAN w/o C2FAblation=Without Coarse-to-Fine module2018.1174.869.63
MGAN w/o PIAblation=Without Position Information2018.1172.9867.71
IAN2018.1172.1—
RAM2018.1172.0868.43
TNDescription=Target Network (proposed base model)2018.1170.5865.34
MemNet2018.1170.3364.09
AE-LSTM2018.1168.9762.5
ATAE-LSTM2018.1168.6562.45
TD-LSTM2018.1168.1862.28