Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Yelp

Benchmarks

Task NameDataset NameSOTA ResultTrend
Sequential RecommendationYelp
NDCG@101.76
131
RecommendationYelp 2018 (test)
Recall@207.83
110
Text ClassificationYelp (test)
Accuracy94.8
100
RecommendationYelp (test)
NDCG@209.82
82
RecommendationYelp 2018
Recall@2019.69
73
Synthetic Text EvaluationYelp non-IID
MAUVE Score0.3751
64
Sequential RecommendationYelp (Overall)
Hit Rate @100.6692
63
Adversarial AttackYelp
ASR72.9
58
Sentiment ClassificationYelp (test)
Accuracy96.4
46
Sequential RecommendationYelp
HR@104.72
45
Collaborative FilteringYelp 2018 (test)
Recall@207.43
45
Adversarial Attack on Neural Contextual BanditsYelp
Regret36
42
Collaborative FilteringYelp 2018
NDCG@205.75
42
Review Sentiment ClassificationYelp 2014 (test)
Accuracy68.6
41
Graph Fraud DetectionYelp (test)
AUROC92.9
40
Sequential RecommendationYelp (Tail)
Hit Rate@1026.93
39
RecommendationYelp
Recall@1036.38
38
Sequential RecommendationYelp (test)
H@104.95
37
Generative RecommendationYelp
N@100.0274
37
Sentiment ClassificationYelp Polarity (test)
Error Rate1.81
37
Text classificationYelp (5-fold cross-validation)
Accuracy71.7
36
Node ClassificationYelp
Accuracy93.4
35
RecommendationYelp
NDCG@107.79
35
Language ModelingYelp (test)
PPL4.708
35
Sequential RecommendationYelp (test)
NDCG@52.68
34
Showing 25 of 292 rows
...