Description
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 Copy S3 URI
How to use
...
lemmatizer = LemmatizerModel.pretrained("lemma", "ru") \
.setInputCols(["token"]) \
.setOutputCol("lemma")
nlp_pipeline = Pipeline(stages=[document_assembler, tokenizer, lemmatizer])
light_pipeline = LightPipeline(nlp_pipeline.fit(spark.createDataFrame([['']]).toDF("text")))
results = light_pipeline.fullAnnotate("Помимо того, что он король севера, Джон Сноу - английский врач и лидер в разработке анестезии и медицинской гигиены.")
...
val lemmatizer = LemmatizerModel.pretrained("lemma", "ru")
.setInputCols(Array("token"))
.setOutputCol("lemma")
val pipeline = new Pipeline().setStages(Array(document_assembler, tokenizer, lemmatizer))
val data = Seq("Помимо того, что он король севера, Джон Сноу - английский врач и лидер в разработке анестезии и медицинской гигиены.").toDF("text")
val result = pipeline.fit(data).transform(data)
import nlu
text = ["""Помимо того, что он король севера, Джон Сноу - английский врач и лидер в разработке анестезии и медицинской гигиены."""]
lemma_df = nlu.load('ru.lemma').predict(text, output_level = "document")
lemma_df.lemma.values[0]
Results
[Row(annotatorType='token', begin=0, end=5, result='помимо', metadata={'sentence': '0'}, embeddings=[]),
Row(annotatorType='token', begin=7, end=10, result='то', metadata={'sentence': '0'}, embeddings=[]),
Row(annotatorType='token', begin=11, end=11, result=',', metadata={'sentence': '0'}, embeddings=[]),
Row(annotatorType='token', begin=13, end=15, result='что', metadata={'sentence': '0'}, embeddings=[]),
Row(annotatorType='token', begin=17, end=18, result='он', metadata={'sentence': '0'}, embeddings=[]),
...]
Model Information
| Model Name: | lemma |
| Type: | lemmatizer |
| Compatibility: | Spark NLP 2.4.4 |
| Edition: | Official |
| Input labels: | [token] |
| Output labels: | [lemma] |
| Language: | ru |
| Case sensitive: | false |
| License: | Open Source |
Data Source
The model is imported from https://universaldependencies.org