Punctuation restoration Model and Spacing Model for Korean Ancient Document
This work addresses the challenge for modern individuals and translation models in accurately interpreting Korean historical texts, though it is incremental as it adapts existing approaches to a new domain.
The researchers tackled the problem of interpreting Korean ancient documents, which lack spacing and punctuation and are written in classical Chinese characters, by developing the first models for punctuation restoration and spacing prediction, achieving F1 scores of 0.84 and 0.96, respectively.
In Korean ancient documents, there is no spacing or punctuation, and they are written in classical Chinese characters. This makes it challenging for modern individuals and translation models to accurately interpret and translate them. While China has models predicting punctuation and spacing, applying them directly to Korean texts is problematic due to data differences. Therefore, we developed the first models which predict punctuation and spacing for Korean historical texts and evaluated their performance. Our punctuation restoration model achieved an F1 score of 0.84, and Spacing model achieved a score of 0.96. It has the advantage of enabling inference on low-performance GPUs with less VRAM while maintaining quite high accuracy.