Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/SciBERT

SciBERT

Reported on 9 benchmarks across 4 tasks · 2 papers · 8 SOTA

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

Methodology4 results

ClassificationonACL-ARC
F1· 2019-03-26
70.98
best: 78.1 (FE-MLM + Span)
SOTA
SciBERT: A Pretrained Language Model for Scientific Text arXiv:1903.10676
ClassificationonSciCite
F1· 2019-03-26
84.9
SOTA
SciBERT: A Pretrained Language Model for Scientific Text arXiv:1903.10676
ClassificationonSciCite
Macro-F1· uses extra data· 2019-03-26
86.32
best: 89.46 (EnsIntWS)
SOTA
SciBERT: A Pretrained Language Model for Scientific Text arXiv:1903.10676
Representation LearningonSciDocs
Avg.· 2020-04-15
59.6
best: 81.8 (SciNCL)
SPECTER: Document-level Representation Learning using Citation-informed Transformers arXiv:2004.07180

Natural Language Processing3 results

Text ClassificationonACL-ARC
F1· 2019-03-26
70.98
best: 78.1 (FE-MLM + Span)
SOTA
SciBERT: A Pretrained Language Model for Scientific Text arXiv:1903.10676
Text ClassificationonSciCite
F1· 2019-03-26
84.9
SOTA
SciBERT: A Pretrained Language Model for Scientific Text arXiv:1903.10676
Text ClassificationonSciCite
Macro-F1· uses extra data· 2019-03-26
86.32
best: 89.46 (EnsIntWS)
SOTA
SciBERT: A Pretrained Language Model for Scientific Text arXiv:1903.10676

Other2 results

Sentence ClassificationonACL-ARC
F1· 2019-03-26
70.98
best: 78.1 (FE-MLM + Span)
SOTA
SciBERT: A Pretrained Language Model for Scientific Text arXiv:1903.10676
Sentence ClassificationonSciCite
F1· 2019-03-26
84.9
SOTA
SciBERT: A Pretrained Language Model for Scientific Text arXiv:1903.10676