NER Pipeline for German

Description

This pretrained pipeline is built on the top of xlm_roberta_large_token_classifier_conll03_de model.

Predicted Entities

Download Copy S3 URI

How to use

pipeline = PretrainedPipeline("xlm_roberta_large_token_classifier_conll03_pipeline", lang = "de")

pipeline.annotate("Ibser begann seine Karriere beim ASK Ebreichsdorf. 2004 wechselte er zu Admira Wacker Mödling, wo er auch in der Akademie spielte.")
val pipeline = new PretrainedPipeline("xlm_roberta_large_token_classifier_conll03_pipeline", lang = "de")

pipeline.annotate("Ibser begann seine Karriere beim ASK Ebreichsdorf. 2004 wechselte er zu Admira Wacker Mödling, wo er auch in der Akademie spielte.")

Results

Results



+----------------------+---------+
|chunk                 |ner_label|
+----------------------+---------+
|Ibser                 |PER      |
|ASK Ebreichsdorf      |ORG      |
|Admira Wacker Mödling |ORG      |
+----------------------+---------+


{:.model-param}

Model Information

Model Name: xlm_roberta_large_token_classifier_conll03_pipeline
Type: pipeline
Compatibility: Spark NLP 4.4.2+
License: Open Source
Edition: Official
Language: de
Size: 1.8 GB

Included Models

  • DocumentAssembler
  • SentenceDetectorDLModel
  • TokenizerModel
  • XlmRoBertaForTokenClassification
  • NerConverter
  • Finisher