GouBook
Goubook
The aim of the project is to develop a Windows application designed to serve as a replacement for the printed textbook of Modern Chinese. The application will integrate available open‑source solutions for phonetic annotation, morphological and syntactic analysis, and it will also incorporate a locally deployed LLM. Naturally, the core functions of the textbook will be preserved, including the text, vocabulary, and optional exercises.
More information in the article.
Phonetic annotation
A prerequisite for phonetic annotation in Chinese is text tokenization. There are several open‑source solutions available in this area. Based on our previous experience with CAT tools, we decided to use the Jieba library, specifically its R implementation, Rjieba. Given the intended purpose, this solution can be considered adequate.






