KEE+NKAM winner of the WSC2016

Reported on 1 benchmark 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 Processing1 result

Coreference ResolutiononWinograd Schema Challenge
Accuracy· 2016-11-13
58.3
best: 100 (PaLM 540B (fine-tuned))
SOTA
Commonsense Knowledge Enhanced Embeddings for Solving Pronoun Disambiguation Problems in Winograd Schema Challenge arXiv:1611.04146