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

NYT

Benchmarks

Task NameDataset NameSOTA ResultTrend
Relation ExtractionNYT (test)
F1 Score92.5
85
Joint Entity and Relation ExtractionNYT (test)
Precision94.7
64
Relation ExtractionNYT 520K (test)
Precision@10092
24
Extractive SummarizationNYT50 (test)
ROUGE-149.47
21
Topic ClassificationNYT (test)
Accuracy92.5
18
Open Information ExtractionNYT
F1 Score85.5
18
Text SummarizationNYT (test)
R1 Score49.18
18
Relational Triple ExtractionNYT standard (test)
F1 Score93.7
16
Extractive Question AnsweringNYT (test)
EM78.11
16
Relation ExtractionNYT HRL 11
Precision56.46
14
Sentence-level Relation ExtractionNYT-10 (test)
Precision76.34
13
Sentence-level Relation ExtractionNYT-10 (dev)
Precision69.94
13
Relation ExtractionNYT29 One-shot
Precision0.6334
12
Multiple-type control summarizationNYT (test)
R150.04
12
Instruction AwarenessNYT (test)
Spearman Correlation64.65
12
Text ClassificationNYT
Micro F192.64
12
Joint Entity and Relation ExtractionNYT
Entity F195.9
12
Relation ExtractionNYT HRL 10
Precision81.19
11
ClusteringNYT
F1 Score72
10
Relation ExtractionNYT-10m (test)
AUC62.2
10
Relation ClassificationNYT (test)
Accuracy85.1
10
Relation ExtractionNYT-570K long-tail (test)
Hits@10 (Macro)81.8
9
Relation ExtractionNYT-570K long-tail (<100 training instances) (test)
Hits@15 (Macro)77.8
9
Knowledge Graph GenerationNYT (test)
F1 Score91.9
9
Relation ExtractionNYT (test)
P@10093.9
9
Showing 25 of 76 rows