NYT
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Relation Extraction | NYT (test) | F1 Score92.5 | 85 | |
| Joint Entity and Relation Extraction | NYT (test) | Precision94.7 | 64 | |
| Hierarchical Text Classification | NYT | Macro F169.76 | 31 | |
| Relation Extraction | NYT 520K (test) | Precision@10092 | 24 | |
| Extractive Summarization | NYT50 (test) | ROUGE-149.47 | 21 | |
| Topic Classification | NYT (test) | Accuracy92.5 | 18 | |
| Open Information Extraction | NYT | F1 Score85.5 | 18 | |
| Text Summarization | NYT (test) | R1 Score49.18 | 18 | |
| Relational Triple Extraction | NYT standard (test) | F1 Score93.7 | 16 | |
| Extractive Question Answering | NYT (test) | EM78.11 | 16 | |
| Relation Extraction | NYT HRL 11 | F1 Score56.23 | 16 | |
| Topic Modeling | NYT corpus | NPMI0.611 | 14 | |
| Sentence-level Relation Extraction | NYT-10 (test) | Precision76.34 | 13 | |
| Sentence-level Relation Extraction | NYT-10 (dev) | Precision69.94 | 13 | |
| Relation Extraction | NYT29 One-shot | Precision0.6334 | 12 | |
| Multiple-type control summarization | NYT (test) | R150.04 | 12 | |
| Instruction Awareness | NYT (test) | Spearman Correlation64.65 | 12 | |
| Text Classification | NYT | Micro F192.64 | 12 | |
| Joint Entity and Relation Extraction | NYT | Entity F195.9 | 12 | |
| Relation Extraction | NYT | F1 Score96.41 | 11 | |
| Relation Extraction | NYT HRL 10 | Precision81.19 | 11 | |
| Clustering | NYT | F1 Score72 | 10 | |
| Relation Extraction | NYT-10m (test) | AUC62.2 | 10 | |
| Relation Classification | NYT (test) | Accuracy85.1 | 10 | |
| Relation Extraction | NYT-570K long-tail (test) | Hits@10 (Macro)81.8 | 9 |
Showing 25 of 77 rows