Cross Lingual Ner On Conll Dutch

Results

Performance results of various models on this benchmark

Model Name	F1	Paper Title	Repository
Base Model	79.57	Enhanced Meta-Learning for Cross-lingual Named Entity Recognition with Minimal Resources
SMTS Multi sim	81.33	Single-/Multi-Source Cross-Lingual NER via Teacher-Student Learning on Unlabeled Data in Target Language
XLM-R large	79.7	Model and Data Transfer for Cross-Lingual Sequence Labelling in Zero-Resource Settings	-
mBERT	77.57	Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERT
SMTS Single	80.89	Single-/Multi-Source Cross-Lingual NER via Teacher-Student Learning on Unlabeled Data in Target Language
UniTrans	82.9	UniTrans: Unifying Model Transfer and Data Transfer for Cross-Lingual Named Entity Recognition with Unlabeled Data
SMTS Multi avg	80.7	Single-/Multi-Source Cross-Lingual NER via Teacher-Student Learning on Unlabeled Data in Target Language
MAN-MoE+CharCNN+UMWE	72.4	Multi-Source Cross-Lingual Model Transfer: Learning What to Share
Meta-Cross	80.44	Enhanced Meta-Learning for Cross-lingual Named Entity Recognition with Minimal Resources
Zero shot mBERT 3	83.35	Towards Lingua Franca Named Entity Recognition with BERT	-

0 of 10 row(s) selected.