DeepEx (zero-shot top-1)

Reported on 4 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing4 results

Relation ExtractiononTACRED
F1· 2021-09-23
49.2
best: 86.6 (RAG4RE)
Zero-Shot Information Extraction as a Unified Text-to-Triple Translation arXiv:2109.11171
Relation ExtractiononFewRel
F1· 2021-09-23
48.8
best: 92.9 (DeepEx (zero-shot top-10))
Zero-Shot Information Extraction as a Unified Text-to-Triple Translation arXiv:2109.11171
Relation ClassificationonTACRED
F1· 2021-09-23
49.2
best: 76.8 (DeepStruct multi-task w/ finetune)
Zero-Shot Information Extraction as a Unified Text-to-Triple Translation arXiv:2109.11171
Relation ClassificationonFewRel
F1· 2021-09-23
48.8
best: 92.9 (DeepEx (zero-shot top-10))
Zero-Shot Information Extraction as a Unified Text-to-Triple Translation arXiv:2109.11171