Word Segmenter for Chinese

Description

WordSegmenterModel-WSM is based on maximum entropy probability model to detect word boundaries in Chinese text. Chinese text is written without white space between the words, and a computer-based application cannot know a priori which sequence of ideograms form a word. In many natural language processing tasks such as part-of-speech (POS) and named entity recognition (NER) require word segmentation as a initial step.

Open in Colab Download

How to use


word_segmenter = WordSegmenterModel.pretrained("wordseg_pku", "zh")        .setInputCols(["sentence"])        .setOutputCol("token")
pipeline = Pipeline(stages=[document_assembler, word_segmenter])
ws_model = pipeline.fit(spark.createDataFrame([[""]]).toDF("text"))
example = spark.createDataFrame(pd.DataFrame({'text': [""从John Snow Labs你好 ""]}))
result = ws_model.transform(example)


val word_segmenter = WordSegmenterModel.pretrained("wordseg_pku", "zh")
        .setInputCols(Array("sentence"))
        .setOutputCol("token")
val pipeline = new Pipeline().setStages(Array(document_assembler, word_segmenter))
val result = pipeline.fit(Seq.empty["从John Snow Labs你好 "].toDS.toDF("text")).transform(data)


import nlu
text = [""从John Snow Labs你好 ""]
token_df = nlu.load('zh.segment_words.pku').predict(text)
token_df
    

Results


0     从
1    Jo
2    hn
3    Sn
4    ow
5    La
6    bs
7     你
8     好
9     !
Name: token, dtype: object

Model Information

Model Name: wordseg_pku
Compatibility: Spark NLP 3.0.0+
License: Open Source
Edition: Official
Input Labels: [document]
Output Labels: [words_segmented]
Language: zh