Stanza

Reported on 3 benchmarks across 2 tasks · 2 papers · 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

Dependency ParsingonUniversal Dependency Treebank
Macro F1· 2020-03-16
81.13
SOTA
Stanza: A Python Natural Language Processing Toolkit for Many Human Languages arXiv:2003.07082
Part-Of-Speech TaggingonUD2.5 test
Macro-averaged F1· 2021-01-09
94.21
best: 95.65 (Trankit)
Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing arXiv:2101.03289
Dependency ParsingonUD2.5 test
Macro-averaged F1· 2021-01-09
83.06
best: 87.06 (Trankit)
Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing arXiv:2101.03289