Overview

This is a project for Chinese Tokenization.

Usage

• Usage of segment_sentences:

    python segment_sentences.py [options] [arg]
  

• Options:

    -h, --help            show this help message and exit
  
    -d, --debug           print the debug information of the segmentation,
                        default is not
  
    -f FILE, --file=FILE  segment sentences from the specified file
  
    -i, --interactive     go into interactive mode
  
    -o OUT, --out=OUT     write the segment result into the specified file
  
    -s SEPARATOR, --separator=SEPARATOR
                        specified the separator of the segmentation result
  
    -t TRAIN, --train=TRAIN
                        use the training set to train the algorithm
  
    -v, --version         output version info and exit