Part of Speech for Latin

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_llct", "la") \
    .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("Alius est esse regem Aquilonis, et de Anglis medicus et nives Ioannes dux in progressus medicinae anesthesia et hygiene.")

val pos = PerceptronModel.pretrained("pos_ud_llct", "la")
    .setInputCols(Array("document", "token"))
    .setOutputCol("pos")

Results

[Row(annotatorType='pos', begin=0, end=4, result='PROPN', metadata={'word': 'Alius'}, embeddings=[]),
Row(annotatorType='pos', begin=6, end=8, result='AUX', metadata={'word': 'est'}, embeddings=[]),
Row(annotatorType='pos', begin=10, end=13, result='VERB', metadata={'word': 'esse'}, embeddings=[]),
Row(annotatorType='pos', begin=15, end=19, result='VERB', metadata={'word': 'regem'}, embeddings=[]),
Row(annotatorType='pos', begin=21, end=29, result='PROPN', metadata={'word': 'Aquilonis'}, embeddings=[]),
...]

Model Information

Model Name: pos_ud_llct
Type: pos
Compatibility: Spark NLP 2.5.5+
Edition: Official
Input labels: [token]
Output labels: [pos]
Language: la
Case sensitive: false
License: Open Source

Data Source

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