Bulgarian 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", "bg") \
        .setInputCols(["token"]) \
nlp_pipeline = Pipeline(stages=[document_assembler, tokenizer, lemmatizer])
light_pipeline = LightPipeline(nlp_pipeline.fit(spark.createDataFrame([['']]).toDF("text")))
results = light_pipeline.fullAnnotate("Освен че е крал на север, Джон Сноу е английски лекар и лидер в развитието на анестезия и медицинска хигиена.")
val lemmatizer = LemmatizerModel.pretrained("lemma", "bg")
val pipeline = new Pipeline().setStages(Array(document_assembler, tokenizer, lemmatizer))
val result = pipeline.fit(Seq.empty["Освен че е крал на север, Джон Сноу е английски лекар и лидер в развитието на анестезия и медицинска хигиена."].toDS.toDF("text")).transform(data)


[Row(annotatorType='token', begin=0, end=4, result='Освен', metadata={'sentence': '0'}, embeddings=[]),
Row(annotatorType='token', begin=6, end=7, result='че', metadata={'sentence': '0'}, embeddings=[]),
Row(annotatorType='token', begin=9, end=9, result='съм', metadata={'sentence': '0'}, embeddings=[]),
Row(annotatorType='token', begin=11, end=14, result='крада', metadata={'sentence': '0'}, embeddings=[]),
Row(annotatorType='token', begin=16, end=17, result='на', metadata={'sentence': '0'}, embeddings=[]),

Model Information

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

Data Source

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