개발 일기

Introduce Khaiii Github Translation Project 본문

Technical Writing/Khaiii Wiki Translation

Introduce Khaiii Github Translation Project

flow123 2021. 6. 24. 17:57

What is Khaiii? 


With an interest in machine learning translation systems, I have found an open-source project called the Khaiii project a couple of months ago. Khaiii has built by Jamie Lim and other Kakao developers in 2018. As introduced in its Github, Khaiii (Kakao Hangul Analyzer III) is the third morphological analyzer developed by Kakao. Morphological analysis is the most basic process in natural language processing (NLP) and the first step in executing syntax or semantic analysis.  NLP is utilized in machine learning, chatbot system, information search, corpus building, deep learning, etc. It is a key to analyze big data as well as understand a human's language processing (AI times

 

Though the team does not actively progress Khaiii anymore, this Github includes many valuable details about how this morphological analyzer is developed, improved, and the team's lesson learned. I have translated some of the key documentation in this section.

 

*You can find translator's notes italicized

*The original document can be found https://github.com/kakao/khaiii. Please note that this document has not been reviewed by the Kakao team and it's just my personal project. Please feel free to provide feedbacks on any error that may occur during the translation process

 


Translator's Note

Introduce Khaiii Github Translation Project: Link

[Khaiii GIthub] Key terms & Concepts: Link

 

Other Khaiii Translation 

[Khaiii Github] Read Me.md: Link

[Khaiii Github] Pre Analysis Dictionary: Link

[Khaiii Github] CNN Model: Link

[Khaiii Github] Test for Specialized Spacing Error Model: Link

[Khaiii Github] CNN Model Training Process: Link

[Khaiii Github]: Analysis Error Patch: Link

Comments