SciBERT (mean pooling / no preprocessing)

Reported on 4 benchmarks across 2 tasks · 1 paper · 4 SOTA

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

Natural Language Processing2 results

Relation ExtractiononSemEval-2022 Task-12
Entity F1 (partial)· 2022-03-10
41.21
best: 47.61 (MRC-based NER + Span pair classification with solid marker + ensemble)
SOTA
AIFB-WebScience at SemEval-2022 Task 12: Relation Extraction First -- Using Relation Extraction to Identify Entities arXiv:2203.05325
Relation ExtractiononSemEval-2022 Task-12
Relation F1· 2022-03-10
32.28
best: 37.19 (MRC-based NER + Span pair classification with solid marker + ensemble)
SOTA
AIFB-WebScience at SemEval-2022 Task 12: Relation Extraction First -- Using Relation Extraction to Identify Entities arXiv:2203.05325

Medical2 results

Information ExtractiononSemEval-2022 Task-12
Entity F1 (partial)· 2022-03-10
41.21
best: 47.61 (MRC-based NER + Span pair classification with solid marker + ensemble)
SOTA
AIFB-WebScience at SemEval-2022 Task 12: Relation Extraction First -- Using Relation Extraction to Identify Entities arXiv:2203.05325
Information ExtractiononSemEval-2022 Task-12
Relation F1· 2022-03-10
32.28
best: 37.19 (MRC-based NER + Span pair classification with solid marker + ensemble)
SOTA
AIFB-WebScience at SemEval-2022 Task 12: Relation Extraction First -- Using Relation Extraction to Identify Entities arXiv:2203.05325