Stop Words Cleaner for Greek

Description

This model removes ‘stop words’ from text. Stop words are words so common that they can removed without significantly altering the meaning of a text. Removing stop words is useful when one wants to deal with only the most semantically important words in a text, and ignore words that are rarely semantically relevant, such as articles and prepositions.

Open in Colab Download

How to use


stop_words = StopWordsCleaner.pretrained("stopwords_el", "el") \
        .setInputCols(["token"]) \
        .setOutputCol("cleanTokens")
nlp_pipeline = Pipeline(stages=[document_assembler, tokenizer, stop_words])
light_pipeline = LightPipeline(nlp_pipeline.fit(spark.createDataFrame([['']]).toDF("text")))
results = light_pipeline.fullAnnotate("Εκτός από το ότι είναι ο βασιλιάς του Βορρά, ο John Snow είναι Άγγλος γιατρός και ηγέτης στην ανάπτυξη της αναισθησίας και της ιατρικής υγιεινής.")

val stopWords = StopWordsCleaner.pretrained("stopwords_el", "el")
        .setInputCols(Array("token"))
        .setOutputCol("cleanTokens")

Results

[Row(annotatorType='token', begin=0, end=4, result='Εκτός', metadata={'sentence': '0'}, embeddings=[]),
Row(annotatorType='token', begin=6, end=8, result='από', metadata={'sentence': '0'}, embeddings=[]),
Row(annotatorType='token', begin=13, end=15, result='ότι', metadata={'sentence': '0'}, embeddings=[]),
Row(annotatorType='token', begin=17, end=21, result='είναι', metadata={'sentence': '0'}, embeddings=[]),
Row(annotatorType='token', begin=25, end=32, result='βασιλιάς', metadata={'sentence': '0'}, embeddings=[]),
...]

Model Information

Model Name: stopwords_el
Type: stopwords
Compatibility: Spark NLP 2.5.4+
Edition: Official
Input Labels: [token]
Output Labels: [cleanTokens]
Language: el
Case sensitive: false
License: Open Source

Data Source

The model is imported from https://github.com/WorldBrain/remove-stopwords