Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Douban

Benchmarks

Task NameDataset NameSOTA ResultTrend
Dialogue GenerationDouban (test)
BLEU-10.1398
20
Multi-turn response selectionDouban (test)
MAP62.7
16
Matrix CompletionDouban
RMSE0.721
15
Graph feature imputationDouban (test)
RMSE0.734
13
Subgraph AlignmentDouban Online-Offline
Hit@175.58
10
RecommendationDouban (test)
RMSE0.732
10
Link PredictionDouban (20% test)
AUC0.8421
9
RecommendationDouban
Recall@2018.61
8
Matrix CompletionDouban (test)
RMSE0.734
7
Rating PredictionDouban
RMSE0.6911
7
Matrix CompletionDouban 1.0
RMSE0.721
6
Short-text GenerationDouban (test)
F1 Score11.02
6
Short-text generationDouban
Informativeness3.44
6
Matrix CompletionDouban 3k
RMSE0.7323
6
Link PredictionDouban 20% edges (test)
AUC82.3
6
Network reconstructionDouban
AUC93
6
Binary ClassificationDOUBAN
Accuracy60.85
3
Matrix CompletionDouban canonical 80/20 (test)
RMSE0.734
3
Recommendation SystemDouban
Model Dimension128
2
Showing 19 of 19 rows