A weakly supervised preference alignment framework for robust ancient Chinese translation
Authors:
- Xiaojun BiXBXiaojun Bi
- Shuo LiSLShuo Li
- Junyao XingJXJunyao Xing
- Yiwen SunYSYiwen Sun
- 24 March 2026
- journal article
- Published by Elsevier in Pattern Recognition
- Vol. 179
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (62236011)
This publication has 13 references indexed in Scilit:
- TIMTQE: Benchmarking Machine Translation Quality Estimation for Text ImagesIEEE Signal Processing Letters, 2025
- A multi agent classical Chinese translation method based on large language modelsScientific Reports, 2025
- Multimodal context-aware translation of the endangered dongba scriptnpj Heritage Science, 2025
- Research on machine translation of ancient books in the era of large language modelnpj Heritage Science, 2025
- Exploiting unlabeled data in few-shot learning with manifold similarity and label cleaningPattern Recognition, 2024
- Dealing with partial labels by knowledge distillationPattern Recognition, 2024
- A survey of context in neural machine translation and its evaluationNatural Language Processing, 2024
- Large-scale continual learning for ancient Chinese character recognitionPattern Recognition, 2024
- Pairwise learning for the partial label ranking problemPattern Recognition, 2023
- Precise detection of Chinese characters in historical documents with deep reinforcement learningPattern Recognition, 2020