SPECTER: Document-level Representation Learning using Citation-informed Transformers

Open paper
Benchmark Model Rank Results
representation-learning-on-scidocsSPECTER#2Avg.: 80.0
representation-learning-on-scidocsCiteomatic#3Avg.: 76.0
representation-learning-on-scidocsSciBERT#5Avg.: 59.6

Rank counts only results with a code link.