List your company
ResearchFormerly WizWand

Implicit Sentiment Analysis on SemEval Laptop ISA 2014

82.43F1 ScoreTHOR
67.03871.03475.0379.026May 18, 2023
Updated 8mo ago

Evaluation results

MethodLinks
THORModel Parameters=11B, Backbone=Flan-T5, Evaluation Protocol=Supervised fine-tuning2023.0582.43
THORModel Parameters=11B, Backbone=Flan-T5, Evaluation Protocol=Supervised fine-tuning, Method Variation=w/o Reason-revising2023.0581.69
THORModel Parameters=11B, Backbone=Flan-T5, Evaluation Protocol=Supervised fine-tuning, Method Variation=w/o Self-consistency2023.0580.27
Flan-T5+PromptModel Parameters=11B, Backbone=Flan-T5, Evaluation Protocol=Supervised fine-tuning2023.0578.91
BERT+ISAIVModel Parameters=110M, Backbone=BERT, Evaluation Protocol=Supervised fine-tuning2023.0578.29
BERTAsp+SCAPTModel Parameters=110M, Backbone=BERT, Evaluation Protocol=Supervised fine-tuning2023.0577.59
Flan-T5+PromptModel Parameters=250M, Backbone=Flan-T5, Evaluation Protocol=Supervised fine-tuning2023.0576.4
BERTAsp+CEPTModel Parameters=110M, Backbone=BERT, Evaluation Protocol=Supervised fine-tuning2023.0575.86
BERT+PromptModel Parameters=110M, Backbone=BERT, Evaluation Protocol=Supervised fine-tuning2023.0575.24
BERT+RGATModel Parameters=110M, Backbone=BERT, Evaluation Protocol=Supervised fine-tuning2023.0572.99
BERT+ADAModel Parameters=110M, Backbone=BERT, Evaluation Protocol=Supervised fine-tuning2023.0570.11
BERT+SPCModel Parameters=110M, Backbone=BERT, Evaluation Protocol=Supervised fine-tuning2023.0569.54
THORModel Parameters=250M, Backbone=Flan-T5, Evaluation Protocol=Supervised fine-tuning2023.0567.63