Chinese 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", "zh") \
        .setInputCols(["token"]) \
nlp_pipeline = Pipeline(stages=[document_assembler, tokenizer, lemmatizer])
light_pipeline = LightPipeline([['']]).toDF("text")))
results = light_pipeline.fullAnnotate("除了担任北方国王之外,约翰·斯诺(John Snow)是一位英国医师,也是麻醉和医疗卫生发展的领导者。")
val lemmatizer = LemmatizerModel.pretrained("lemma", "zh")
val pipeline = new Pipeline().setStages(Array(document_assembler, tokenizer, lemmatizer))
val result =["除了担任北方国王之外约翰·斯诺John Snow是一位英国医师也是麻醉和医疗卫生发展的领导者。"].toDS.toDF("text")).transform(data)
import nlu

text = ["""除了担任北方国王之外,约翰·斯诺(John Snow)是一位英国医师,也是麻醉和医疗卫生发展的领导者。"""]
lemma_df = nlu.load('zh.lemma').predict(text, output_level='document')


[Row(annotatorType='token', begin=0, end=20, result='除了担任北方国王之外,约翰·斯诺(John', metadata={'sentence': '0'}, embeddings=[]),
Row(annotatorType='token', begin=22, end=50, result='Snow)是一位英国医师,也是麻醉和医疗卫生发展的领导者。', 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: zh
Case sensitive: false
License: Open Source

Data Source

The model is imported from