List your company
ResearchFormerly WizWand

Question Answering on MOCHA (test)

0.741Pearson's rMARS (default)
-0.162760.071870.30650.54113Aug 19, 2021
Updated 8mo ago

Evaluation results

MethodLinks
MARS (default)NLG System=MHPG2021.080.741
MARS w/o. self-plan.NLG System=MHPG2021.080.709
MARS (default)NLG System=Back-Tran2021.080.644
MARS w/o. self-plan.NLG System=Back-Tran2021.080.631
Sentence Mover's SimilarityNLG System=MHPG2021.080.61
MoverScoreNLG System=MHPG2021.080.592
Naive (MLM)NLG System=MHPG2021.080.54
MoverScoreNLG System=GPT-22021.080.535
MARS (default)NLG System=GPT-22021.080.526
Sentence Mover's SimilarityNLG System=GPT-22021.080.51
MARS w/o. self-plan.NLG System=GPT-22021.080.477
ROUGE-LNLG System=GPT-22021.080.468
METEORNLG System=GPT-22021.080.466
BERTScoreNLG System=MHPG2021.080.458
BERTScoreNLG System=GPT-22021.080.444
Naive (MLM)NLG System=GPT-22021.080.443
METEORNLG System=MHPG2021.080.409
BLEU-1NLG System=GPT-22021.080.328
BLEU-1NLG System=MHPG2021.080.318
Naive (MLM)NLG System=Back-Tran2021.080.307
MARS w/o. contextNLG System=MHPG2021.080.303
MARS w/o. bothNLG System=MHPG2021.080.299
BERTScoreNLG System=Back-Tran2021.080.274
ROUGE-LNLG System=MHPG2021.080.247
MARS w/o. contextNLG System=Back-Tran2021.080.222
MoverScoreNLG System=Back-Tran2021.080.19
METEORNLG System=Back-Tran2021.080.179
Sentence Mover's SimilarityNLG System=Back-Tran2021.080.166
MARS w/o. contextNLG System=GPT-22021.080.134
MARS w/o. bothNLG System=Back-Tran2021.080.121
BLEU-1NLG System=Back-Tran2021.080.061
ROUGE-LNLG System=Back-Tran2021.080.056
PerplexityNLG System=GPT-22021.080.014
PerplexityNLG System=Back-Tran2021.08-0.051
MARS w/o. bothNLG System=GPT-22021.08-0.092
PerplexityNLG System=MHPG2021.08-0.128