Pretrained Pipeline for Few-NERD-General NER Model

Description

This pretrained pipeline is built on Few-NERD model and it detects :

PERSON, ORGANIZATION, LOCATION, ART, BUILDING, PRODUCT, EVENT, OTHER

Predicted Entities

Download Copy S3 URI

How to use

fewnerd_pipeline = PretrainedPipeline("nerdl_fewnerd_subentity_100d_pipeline", lang = "en")

fewnerd_pipeline.annotate("""The Double Down is a sandwich offered by Kentucky Fried Chicken restaurants. He did not see active service again until 1882, when he took part in the Anglo-Egyptian War, and was present at the battle of Tell El Kebir (September 1882), for which he was mentioned in dispatches, received the Egypt Medal with clasp and the 3rd class of the Order of Medjidie, and was appointed a Companion of the Order of the Bath (CB).""")
val pipeline = new PretrainedPipeline("nerdl_fewnerd_subentity_100d_pipeline", lang = "en")

val result = pipeline.fullAnnotate("The Double Down is a sandwich offered by Kentucky Fried Chicken restaurants. He did not see active service again until 1882, when he took part in the Anglo-Egyptian War, and was present at the battle of Tell El Kebir (September 1882), for which he was mentioned in dispatches, received the Egypt Medal with clasp and the 3rd class of the Order of Medjidie, and was appointed a Companion of the Order of the Bath (CB).")(0)

Results

Results



+-----------------------+------------+
|chunk                  |ner_label   |
+-----------------------+------------+
|Kentucky Fried Chicken |ORGANIZATION|
|Anglo-Egyptian War     |EVENT       |
|battle of Tell El Kebir|EVENT       |
|Egypt Medal            |OTHER       |
|Order of Medjidie      |OTHER       |
+-----------------------+------------+


{:.model-param}

Model Information

Model Name: nerdl_fewnerd_100d_pipeline
Type: pipeline
Compatibility: Spark NLP 4.4.2+
License: Open Source
Edition: Official
Language: en
Size: 167.3 MB

Included Models

  • DocumentAssembler
  • SentenceDetector
  • TokenizerModel
  • WordEmbeddingsModel
  • NerDLModel
  • NerConverter
  • Finisher