BERT (gold POS/lemmas)

Reported on 4 benchmarks across 1 task · 1 paper

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

Natural Language Processing4 results

Natural Language UnderstandingonSTREUSLE
Full F1 (Preps)· 2020-04-30
71.4
best: 78.2 (RoBERTa + Linear)
Lexical Semantic Recognition arXiv:2004.15008
Natural Language UnderstandingonSTREUSLE
Function F1 (Preps)· 2020-04-30
81.7
best: 82.8 (BERT (pred POS/lemmas))
Lexical Semantic Recognition arXiv:2004.15008
Natural Language UnderstandingonSTREUSLE
Role F1 (Preps)· 2020-04-30
72.4
Lexical Semantic Recognition arXiv:2004.15008
Natural Language UnderstandingonSTREUSLE
Tags (Full) Acc· 2020-04-30
81
best: 82.5 (BERT (pred POS/lemmas))
Lexical Semantic Recognition arXiv:2004.15008