metadata

language:
  - nl
tags:
  - Named Entity Recognition
  - xlm-roberta
datasets:
  - conll2002
metrics:
  - f1: 90.57

XLM-RoBERTa base ConLL-2002 Dutch

XLM-Roberta base model finetuned on ConLL-2002 Dutch train set, which is a Named Entity Recognition dataset containing the following classes: PER, LOC, ORG and MISC.

Label mapping: { 0: O, 1: B-PER, 2: I-PER, 3: B-ORG, 4: I-ORG, 5: B-LOC, 6: I-LOC, 7: B-MISC, 8: I-MISC, }

Results from https://arxiv.org/pdf/1911.02116.pdf reciprocated (original results were 90.39 F1, this finetuned version here scored 90.57).