Stanford+

Reported on 3 benchmarks across 1 task · 1 paper · 2 SOTA

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

Natural Language Processing3 results

Dependency ParsingonUniversal Dependencies
BLEX· 2019-01-29
65.28
best: 66.09 (TurkuNLP)
SOTA
Universal Dependency Parsing from Scratch arXiv:1901.10457
Dependency ParsingonUniversal Dependencies
UAS· 2019-01-29
62.08
best: 87.64 (UDPipe 2.0 + mBERT + FLAIR)
SOTA
Universal Dependency Parsing from Scratch arXiv:1901.10457
Dependency ParsingonUniversal Dependencies
LAS· 2019-01-29
74.16
best: 84.6 (UDPipe 2.0 + mBERT + FLAIR)
Universal Dependency Parsing from Scratch arXiv:1901.10457