Subword-level Transformer LM

Reported on 2 benchmarks across 2 tasks · 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 Processing2 results

Natural Language UnderstandingonPDP60
Accuracy· 2017-06-12
58.3
best: 90 (HNN)
SOTA
Attention Is All You Need arXiv:1706.03762
Coreference ResolutiononWinograd Schema Challenge
Accuracy· 2017-06-12
54.1
best: 100 (PaLM 540B (fine-tuned))
Attention Is All You Need arXiv:1706.03762