pycantonese.word_segmentation.Segmenter
- class pycantonese.word_segmentation.Segmenter(*, max_word_length=5, allow=None, disallow=None)[source]
A customizable word segmentation model.
New in version 3.0.0.
Methods
fit(sents)Train the model with the input segmented sentences.
predict(sent_strs)Segment the given unsegmented sentences.
- __init__(*, max_word_length=5, allow=None, disallow=None)[source]
Initialize a Segmenter object.
- Parameters
- max_word_lengthint, optional
Maximum word length this model allows.
- allowiterable[str], optional
Words to allow in word segmentation.
- disallowiterable[str], optional
Words to disallow in word segmentation.
Methods
__init__(*[, max_word_length, allow, disallow])Initialize a Segmenter object.
fit(sents)Train the model with the input segmented sentences.
predict(sent_strs)Segment the given unsegmented sentences.