Successful acceptance of the task "Building an automated system for converting Nôm script to Vietnamese script."
The Department of Science and Technology of Ho Chi Minh City recently organized a council to accept the scientific and technological task "Building an automated system for converting Nôm script to Vietnamese script". This task was led by the University of Sciences (Vietnam National University Ho Chi Minh City) and Assoc. Prof. Dr. Dinh Dien, Deputy Head of the Department of Knowledge Engineering, was the head of the task.
The project team focused on translating from the Nôm script to the Vietnamese script. The team built a Nôm-Vietnamese dictionary (which is essentially a set of Nôm characters with their Vietnamese definitions) to focus on the meaning of each character, providing in-depth linguistic information. The number of Nôm characters extracted from the Nôm language database and reference sources reached 22,264 characters. Then, the team built a Nôm-Vietnamese dictionary containing 6,198 words. The team also built a Chinese-Vietnamese character dictionary with 26,330 characters and a Chinese-Vietnamese word dictionary with 66,450 words.
The project team successfully built language and translation models based on the collected data and built a website to support the automatic conversion of the Nôm script to Vietnamese script (filed for copyright registration). As a result, the task's outcome can be applied to translate Nôm documents on medicine, literature, history, and geography and contribute to preserving and promoting the traditional cultural values of the Vietnamese people.
Source: CESTI: https://cesti.gov.vn/bai-viet/CTDS1/nghiem-thu-nhiem-vu-xay-dung-he-thong-chuyen-tu-tu-dong-van-ban-chu-nom-sang-chu-quoc-ngu-a3bc4756-1584-4c1f-b12b-78e72b0d0739?mibextid=Zxz2cZ