List your company
ResearchFormerly WizWand

Aspect-based Sentiment Analysis on SemEval Restaurant 2014 (All)

87.45F1 ScoreTHOR
32.714846.924961.13575.3451May 18, 2023May 27, 2023Jun 6, 2023Jun 15, 2023Jun 25, 2023Jul 4, 2023Jul 14, 2023
Updated 8mo ago

Evaluation results

MethodLinks
THORModel Parameters=11B, Backbone=Flan-T5, Evaluation Protocol=Supervised fine-tuning2023.0587.45——
THORModel Parameters=11B, Backbone=Flan-T5, Evaluation Protocol=Supervised fine-tuning, Method Variation=w/o Reason-revising2023.0586.88——
THORModel Parameters=11B, Backbone=Flan-T5, Evaluation Protocol=Supervised fine-tuning, Method Variation=w/o Self-consistency2023.0586.03——
Flan-T5+PromptModel Parameters=11B, Backbone=Flan-T5, Evaluation Protocol=Supervised fine-tuning2023.0584.72——
BERTAsp+SCAPTModel Parameters=110M, Backbone=BERT, Evaluation Protocol=Supervised fine-tuning2023.0583.79——
THORModel Parameters=250M, Backbone=Flan-T5, Evaluation Protocol=Supervised fine-tuning2023.0582.98——
BERTAsp+CEPTModel Parameters=110M, Backbone=BERT, Evaluation Protocol=Supervised fine-tuning2023.0582.07——
Flan-T5+PromptModel Parameters=250M, Backbone=Flan-T5, Evaluation Protocol=Supervised fine-tuning2023.0581.5——
BERT+ISAIVModel Parameters=110M, Backbone=BERT, Evaluation Protocol=Supervised fine-tuning2023.0581.4——
BERT+RGATModel Parameters=110M, Backbone=BERT, Evaluation Protocol=Supervised fine-tuning2023.0581.35——
BERT+PromptModel Parameters=110M, Backbone=BERT, Evaluation Protocol=Supervised fine-tuning2023.0581.34——
BERT+ADAModel Parameters=110M, Backbone=BERT, Evaluation Protocol=Supervised fine-tuning2023.0580.05——
BERT+SPCModel Parameters=110M, Backbone=BERT, Evaluation Protocol=Supervised fine-tuning2023.0577.16——
Extra2023.0760.0954.766.67
CoTAMshot_number (K)=10, generation_count (N)=3, backbone=RoBERTa-Large, embedding_model=SimCSE2023.0756.365064.58
FlipDA++2023.0751.3845.958.33
LLM SL2023.0749.5444.2656.25
CoTDA2023.0747.5744.5551.04
Base2023.0734.8230.6140.38