Part of Speech for Finnish

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.

Open in Colab Download

How to use


pos = PerceptronModel.pretrained("pos_ud_tdt", "fi") \
    .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("Sen lisäksi, että hän on pohjoisen kuningas, John Snow on englantilainen lääkäri ja johtava anestesian ja lääketieteellisen hygienian kehittämisessä.")

val pos = PerceptronModel.pretrained("pos_ud_tdt", "fi")
    .setInputCols(Array("document", "token"))
    .setOutputCol("pos")

Results

[Row(annotatorType='pos', begin=0, end=2, result='PRON', metadata={'word': 'Sen'}, embeddings=[]),
Row(annotatorType='pos', begin=4, end=10, result='ADP', metadata={'word': 'lisäksi'}, embeddings=[]),
Row(annotatorType='pos', begin=11, end=11, result='PUNCT', metadata={'word': ','}, embeddings=[]),
Row(annotatorType='pos', begin=13, end=16, result='SCONJ', metadata={'word': 'että'}, embeddings=[]),
Row(annotatorType='pos', begin=18, end=20, result='PRON', metadata={'word': 'hän'}, embeddings=[]),
...]

Model Information

Model Name: pos_ud_tdt
Type: pos
Compatibility: Spark NLP 2.5.0+
Edition: Official
Input labels: [token]
Output labels: [pos]
Language: fi
Case sensitive: false
License: Open Source

Data Source

The model is imported from https://universaldependencies.org