Part of Speech for Romanian

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_rrt", "ro") \
    .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("În afară de a fi regele nordului, John Snow este un medic englez și un lider în dezvoltarea anesteziei și igienei medicale.")

val pos = PerceptronModel.pretrained("pos_ud_rrt", "ro")
    .setInputCols(Array("document", "token"))
    .setOutputCol("pos")

Results

[Row(annotatorType='pos', begin=0, end=1, result='ADP', metadata={'word': 'În'}, embeddings=[]),
Row(annotatorType='pos', begin=3, end=7, result='ADV', metadata={'word': 'afară'}, embeddings=[]),
Row(annotatorType='pos', begin=9, end=10, result='ADP', metadata={'word': 'de'}, embeddings=[]),
Row(annotatorType='pos', begin=12, end=12, result='PART', metadata={'word': 'a'}, embeddings=[]),
Row(annotatorType='pos', begin=14, end=15, result='AUX', metadata={'word': 'fi'}, embeddings=[]),
...]

Model Information

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

Data Source

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