Part of Speech for Norwegian

Description

This model annotates the part of speech of tokens in a text. The parts of speech annotated include PRON (pronoun), CCONJ (coordinating conjunction), and 15 others. The part of speech model is useful for extracting the grammatical structure of a piece of text automatically.

This model was trained using the dataset available at https://universaldependencies.org

Predicted Entities

Download Copy S3 URI

How to use

pos = PerceptronModel.pretrained("pos_ud_bokmaal", "nb") \
    .setInputCols(["document", "token"]) \
    .setOutputCol("pos")

nlp_pipeline = Pipeline(stages=[document_assembler, sentence_detector, tokenizer, pos])
light_pipeline = LightPipeline(nlp_pipeline.fit(spark.createDataFrame([['']]).toDF("text")))
results = light_pipeline.fullAnnotate("Annet enn å være kongen i nord, er John Snow en engelsk lege og en leder innen utvikling av anestesi og medisinsk hygiene.")
val pos = PerceptronModel.pretrained("pos_ud_bokmaal", "nb")
    .setInputCols(Array("document", "token"))
    .setOutputCol("pos")

val pipeline = new Pipeline().setStages(Array(document_assembler, sentence_detector, tokenizer, pos))
val data = Seq("Annet enn å være kongen i nord, er John Snow en engelsk lege og en leder innen utvikling av anestesi og medisinsk hygiene.").toDF("text")
val result = pipeline.fit(data).transform(data)
import nlu

text = ["""Annet enn å være kongen i nord, er John Snow en engelsk lege og en leder innen utvikling av anestesi og medisinsk hygiene."""]
pos_df = nlu.load('nb.pos.ud_bokmaal').predict(text)
pos_df

Results

Results



[Row(annotatorType='pos', begin=0, end=4, result='DET', metadata={'word': 'Annet'}),
Row(annotatorType='pos', begin=6, end=8, result='SCONJ', metadata={'word': 'enn'}),
Row(annotatorType='pos', begin=10, end=10, result='PART', metadata={'word': 'å'}),
Row(annotatorType='pos', begin=12, end=15, result='AUX', metadata={'word': 'være'}),
Row(annotatorType='pos', begin=17, end=22, result='NOUN', metadata={'word': 'kongen'}),
...]


{:.model-param}

Model Information

Model Name: pos_ud_bokmaal
Type: pipeline
Compatibility: Spark NLP 4.4.2+
License: Open Source
Edition: Official
Language: nb
Size: 17.7 KB

Included Models

  • DocumentAssembler
  • SentenceDetector
  • TokenizerModel
  • PerceptronModel