Part of Speech for Portuguese

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_bosque", "pt") \
    .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("Além de ser o rei do norte, John Snow é um médico inglês e líder no desenvolvimento de anestesia e higiene médica.")

val pos = PerceptronModel.pretrained("pos_ud_bosque", "pt")
    .setInputCols(Array("document", "token"))
    .setOutputCol("pos")

Results

[Row(annotatorType='pos', begin=0, end=3, result='ADV', metadata={'word': 'Além'}, embeddings=[]),
Row(annotatorType='pos', begin=5, end=6, result='ADP', metadata={'word': 'de'}, embeddings=[]),
Row(annotatorType='pos', begin=8, end=10, result='AUX', metadata={'word': 'ser'}, embeddings=[]),
Row(annotatorType='pos', begin=12, end=12, result='DET', metadata={'word': 'o'}, embeddings=[]),
Row(annotatorType='pos', begin=14, end=16, result='NOUN', metadata={'word': 'rei'}, embeddings=[]),
...]

Model Information

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

Data Source

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