Stop Words Cleaner for Arabic

Description

This model removes ‘stop words’ from text. Stop words are words so common that they can be 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_ar", "ar") \
        .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("بخلاف كونه ملك الشمال ، فإن جون سنو طبيب إنجليزي ورائد في تطوير التخدير والنظافة الطبية.")
...
val stopWords = StopWordsCleaner.pretrained("stopwords_ar", "ar")
        .setInputCols(Array("token"))
        .setOutputCol("cleanTokens")
val pipeline = new Pipeline().setStages(Array(document_assembler, tokenizer, stopWords))
val result = pipeline.fit(Seq.empty["بخلاف كونه ملك الشمال ، فإن جون سنو طبيب إنجليزي ورائد في تطوير التخدير والنظافة الطبية."].toDS.toDF("text")).transform(data)

Results

[Row(annotatorType='token', begin=0, end=4, result='بخلاف', metadata={'sentence': '0'}),
Row(annotatorType='token', begin=6, end=9, result='كونه', metadata={'sentence': '0'}),
Row(annotatorType='token', begin=11, end=13, result='ملك', metadata={'sentence': '0'}),
Row(annotatorType='token', begin=15, end=20, result='الشمال', metadata={'sentence': '0'}),
Row(annotatorType='token', begin=24, end=26, result='فإن', metadata={'sentence': '0'}),
...]

Model Information

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

Data Source

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