Maltese Lemmatizer

Description

This is a dictionary-based lemmatizer that assigns 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.

Live Demo Open in Colab Download

How to use

document_assembler = DocumentAssembler() \
    .setInputCol("text") \
    .setOutputCol("document")

tokenizer = Tokenizer()\
    .setInputCols(["document"]) \
    .setOutputCol("token")

lemmatizer = LemmatizerModel.pretrained("lemma", "mt") \
        .setInputCols(["token"]) \
        .setOutputCol("lemma")

pipeline = Pipeline(stages=[document_assembler, tokenizer, lemmatizer])

example = spark.createDataFrame(pd.DataFrame({'text': ["""Il- Membru tal- Kumitat Leo Brincat talab li bħala xhud ikun hemm rappreżentant tal- MEPA u kien hemm qbil filwaqt li d- Deputat Laburista Joe Mizzi ta lista ta' persuni oħrajn mill- Korporazzjoni Enemalta u minn WasteServ u ma kienx hemm oġġezzjoni ."""]]}))

results = pipeline.fit(example).transform(example)
val document_assembler = DocumentAssembler()
    .setInputCol("text")
    .setOutputCol("document")

val tokenizer = Tokenizer()
    .setInputCols(["document"])
    .setOutputCol("token")

val lemmatizer = LemmatizerModel.pretrained("lemma", "mt")
        .setInputCols(["token"])
        .setOutputCol("lemma")

val pipeline = new Pipeline().setStages(Array(document_assembler, tokenizer, lemmatizer))
val result = pipeline.fit(Seq.empty["Il- Membru tal- Kumitat Leo Brincat talab li bħala xhud ikun hemm rappreżentant tal- MEPA u kien hemm qbil filwaqt li d- Deputat Laburista Joe Mizzi ta lista ta' persuni oħrajn mill- Korporazzjoni Enemalta u minn WasteServ u ma kienx hemm oġġezzjoni ."].toDS.toDF("text")).transform(data)
import nlu

text = ["Il- Membru tal- Kumitat Leo Brincat talab li bħala xhud ikun hemm rappreżentant tal- MEPA u kien hemm qbil filwaqt li d- Deputat Laburista Joe Mizzi ta lista ta' persuni oħrajn mill- Korporazzjoni Enemalta u minn WasteServ u ma kienx hemm oġġezzjoni ."]
lemma_df = nlu.load('mt.lemma').predict(text, output_level = "document")
lemma_df.lemma.values[0]

Results

+-------+
|  lemma|
+-------+
|     Il|
|      _|
|      _|
|    tal|
|      _|
|      _|
|    Leo|
|Brincat|
|      _|
|      _|
|      _|
|      _|
|      _|
|      _|
|      _|
|    tal|
|      _|
|   MEPA|
|      _|
|      _|
+-------+
only showing top 20 rows

Model Information

Model Name: lemma
Compatibility: Spark NLP 2.7.5+
License: Open Source
Edition: Official
Input Labels: [token]
Output Labels: [lemma]
Language: mt

Data Source

The model was trained on the Universal Dependencies version 2.7.

Benchmarking

Precision=0.078, Recall=0.073, F1-score=0.075