CCExtractor Development

[AI][Medium] Chinese Word Segmentation

Introduction

Chinese language is linguistically very different from English and one of its distinguished linguistic property is that it doesn't contain spaces in the sentences which makes us difficult to distinguish between the words or tokens that can be aligned to the words in other languages.

Skills

  • Natural language processing
  • Machine learning

Task

The task is to make computer program that will take a sentence as an input and will output the segmented sentence or a list of words in the original sentence. Use of external libraries is allowed.To complete the task send a link to a git repository with it.

Task tags

  • ai
  • natural language processing
  • research
  • machine learning

Students who completed this task

AlephZero

Task type

  • code Code
  • assessment Outreach / Research
close

2019