njuseg 1.1

General Chinese Word Segmenter provided by Nanjing University NLP Group

Author:

Saltychtao

Contents

• 1 NJU Chinese Word Segmenter

  • 1.1 Description

  • 1.2 Required Dependency

  • 1.3 Usage

1 NJU Chinese Word Segmenter

1.1 Description

This package contains the Chinese word segmenter released by the natural language processing group of Nanjing University.

1.2 Required Dependency

• Python 3.6

• Numpy

• dyNET >= 2.0

1.3 Usage

1.3.1 Quick Start

Below is a quick snippet of code that demonstrates how to use the API this package provides.

from njuseg.model import Segmenter

 # load a pretrained segmentation model.
segmenter.load('path/to/model')

 # segment a Chinese sentence, note that the sentence should be encoded by utf-8.
segmenter.seg(“上海浦东开发与法制建设同步。”)