longdoc S (ON + PreCo + LitBank + 30k pseudo-singletons)

Reported on 3 benchmarks across 1 task · 1 paper · 1 SOTA

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

Natural Language Processing3 results

Coreference ResolutiononWikiCoref
F1· 2021-09-20
62.5
best: 66.8 (Maverick_mes)
SOTA
On Generalization in Coreference Resolution arXiv:2109.09667
Coreference ResolutiononOntoNotes
F1· 2021-09-20
79.6
best: 83.6 (Maverick_mes)
On Generalization in Coreference Resolution arXiv:2109.09667
Coreference ResolutiononWinograd Schema Challenge
Accuracy· 2021-09-20
59.4
best: 100 (PaLM 540B (fine-tuned))
On Generalization in Coreference Resolution arXiv:2109.09667