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.
How to use
...
lemmatizer = LemmatizerModel.pretrained("lemma", "uk") \
.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("За винятком того, що є королем півночі, Джон Сноу є англійським лікарем та лідером у розвитку анестезії та медичної гігієни.")
...
val lemmatizer = LemmatizerModel.pretrained("lemma", "uk")
.setInputCols(Array("token"))
.setOutputCol("lemma")
val pipeline = new Pipeline().setStages(Array(document_assembler, tokenizer, lemmatizer))
val result = pipeline.fit(Seq.empty["За винятком того, що є королем півночі, Джон Сноу є англійським лікарем та лідером у розвитку анестезії та медичної гігієни."].toDS.toDF("text")).transform(data)
Results
[Row(annotatorType='token', begin=0, end=1, result='За', metadata={'sentence': '0'}, embeddings=[]),
Row(annotatorType='token', begin=3, end=10, result='виняток', metadata={'sentence': '0'}, embeddings=[]),
Row(annotatorType='token', begin=12, end=15, result='те', metadata={'sentence': '0'}, embeddings=[]),
Row(annotatorType='token', begin=16, end=16, result=',', metadata={'sentence': '0'}, embeddings=[]),
Row(annotatorType='token', begin=18, end=19, result='що', 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: | uk |
| Case sensitive: | false |
| License: | Open Source |
Data Source
The model is imported from https://universaldependencies.org
PREVIOUSFinnish Lemmatizer