Description
This pretrained pipeline is built on the top of distilbert_token_classifier_typo_detector.
Predicted Entities
How to use
typo_pipeline = PretrainedPipeline("distilbert_token_classifier_typo_detector_pipeline", lang = "en")
typo_pipeline.annotate("He had also stgruggled with addiction during his tine in Congress.")
val typo_pipeline = new PretrainedPipeline("distilbert_token_classifier_typo_detector_pipeline", lang = "en")
typo_pipeline.annotate("He had also stgruggled with addiction during his tine in Congress.")
Results
Results
+----------+---------+
|chunk |ner_label|
+----------+---------+
|stgruggled|PO |
|tine |PO |
+----------+---------+
{:.model-param}
Model Information
| Model Name: | distilbert_token_classifier_typo_detector_pipeline |
| Type: | pipeline |
| Compatibility: | Spark NLP 4.4.2+ |
| License: | Open Source |
| Edition: | Official |
| Language: | en |
| Size: | 244.1 MB |
Included Models
- DocumentAssembler
- TokenizerModel
- DistilBertForTokenClassification
- NerConverter
- Finisher