Translation via Annotation: A Computational Study of Translating Classical Chinese into Japanese

2025/11/07 by Li, Zilong, Cao, Jie
Biochemistry, Genetics and Molecular Biology · Computer Science · #Annotation #Biomedical Text Mining and Ontologies #Machine translation #Natural Language Processing Techniques #Pipeline (software) #Process (computing) #Quality (philosophy) #Resource (disambiguation) #Sequence (biology) #Topic Modeling #Translation (biology)

paper · open access · doi:10.48550/arxiv.2511.05239

published in arXiv (Cornell University) (Cornell University)

openalex publication_date 2025/11/07 · openalex created_date 2025/11/11 · openalex updated_date 2026/07/28

Abstract

Ancient people translated classical Chinese into Japanese using a system of annotations placed around characters. We abstract this process as sequence tagging tasks and fit them into modern language technologies. The research on this annotation and translation system faces a low resource problem. We alleviate this problem by introducing an LLM-based annotation pipeline and constructing a new dataset from digitized open-source translation data. We show that in the low-resource setting, introducing auxiliary Chinese NLP tasks enhances the training of sequence tagging tasks. We also evaluate the performance of Large Language Models (LLMs) on this task. While they achieve high scores on direct machine translation, our method could serve as a supplement to LLMs to improve the quality of character's annotation.

Citations

• 4 and 7-bit Labeling for Projective and Non-Projective Dependency Trees
• Kanbun-LM: Reading and Translating Classical Chinese in Japanese Methods by Language Models
• A Survey of Multi-task Learning in Natural Language Processing: Regarding Task Relatedness and Training Methods
• The Stem Cell Hypothesis: Dilemma behind Multi-Task Learning with Transformer Encoders
• Time-Aware Ancient Chinese Text Translation and Inference
• JASS: Japanese-specific Sequence to Sequence Pre-training for Neural Machine Translation
• BERTScore: Evaluating Text Generation with BERT
• A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks
• Composita and its properties
• Large Language Models for Classical Chinese Poetry Translation: Benchmarking, Evaluating, and Improving

Related

• Kanbun-LM: Reading and Translating Classical Chinese in Japanese Methods by Language Models
• Efficiently Building a Domain-Specific Large Language Model from Scratch: A Case Study of a Classical Chinese Large Language Model
• Pre-training via Leveraging Assisting Languages and Data Selection for Neural Machine Translation
• A Bilingual Parallel Corpus with Discourse Annotations
• Breaking the Representation Bottleneck of Chinese Characters: Neural Machine Translation with Stroke Sequence Modeling