Marathi Lemmatizer


This model uses context and language knowledge to assign all forms and inflections of a word to a single root. This enables the pipeline to treat the past and present tense of a verb, for example, as the same word instead of two completely different words. The lemmatizer takes into consideration the context surrounding a word to determine which root is correct when the word form alone is ambiguous.

Open in Colab Download

How to use

lemmatizer = LemmatizerModel.pretrained("lemma", "mr") \
        .setInputCols(["token"]) \
nlp_pipeline = Pipeline(stages=[document_assembler, tokenizer, lemmatizer])
light_pipeline = LightPipeline([['']]).toDF("text")))
results = light_pipeline.fullAnnotate("उत्तरेचा राजा होण्याव्यतिरिक्त, जॉन स्नो एक इंग्रज चिकित्सक आहे आणि भूल आणि वैद्यकीय स्वच्छतेच्या विकासासाठी अग्रगण्य आहे.")
val lemmatizer = LemmatizerModel.pretrained("lemma", "mr")
val pipeline = new Pipeline().setStages(Array(document_assembler, tokenizer, lemmatizer))
val result =["उततर  यतिि,   एक रज ििसक आह आणि  आणि यक वचछत ि अगरगण आह."].toDS.toDF("text")).transform(data)


[Row(annotatorType='token', begin=0, end=7, result='उत्तरेचा', metadata={'sentence': '0'}, embeddings=[]),
Row(annotatorType='token', begin=9, end=12, result='राजा', metadata={'sentence': '0'}, embeddings=[]),
Row(annotatorType='token', begin=14, end=29, result='होण्याव्यतिरिक्त', metadata={'sentence': '0'}, embeddings=[]),
Row(annotatorType='token', begin=30, end=30, result=',', metadata={'sentence': '0'}, embeddings=[]),
Row(annotatorType='token', begin=32, end=34, result='जॉन', metadata={'sentence': '0'}, embeddings=[]),

Model Information

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

Data Source

The model is imported from