Xiaoxin Sun

Author directory

2026

Research in cross-lingual modeling for historical and extremely low-resource languages is hindered by the absence of standardized evaluation benchmarks. To address this, we present ManCC—the first task-anchored benchmark for Manchu–Classical Chinese translation. ManCC consists of a high-quality parallel corpus of 16,627 sentence pairs, derived from the Qing-dynasty historical text Manwen Laodang-Taizong, and a reproducible evaluation protocol that combines automatic metrics (BLEU and chrF) with a three-dimensional human assessment (fidelity, fluency, linguistic normativity). Through systematic evaluation across three model families (non-pretrained, multilingual pretrained, and large language models), we find that linguistic differences significantly influence performance, broader language coverage in multilingual pretraining facilitates low-resource transfer, and automatic metrics often fail to capture essential errors in historical translation—underscoring the necessity of human evaluation. ManCC not only provides foundational resources for Manchu–Classical Chinese translation but also establishes a diagnosable, reproducible platform for cross-lingual modeling of historical low-resource languages.
Manchu is a typical low-resource agglutinative language, for which existing digital resources are largely limited to character recognition and basic annotation, while sentence-level generation remains underexplored. In this paper, we study constrained sentence-level Manchu continuation. We construct the first context-target corpus for this continuation task, consisting of 3214 examples collected from Manchu Stories in Translation, Common Manchu Dialogues, and other sources, covering both narrative and conversational genres. To improve robustness to rich suffixation, relatively flexible word order, and frequent OCR or transcription noise in Manchu, we propose a Multi-Granularity Data Augmentation (MGDA) strategy that expands training data through character-level noise injection, phrase rearrangement, and suffix perturbation, without relying on external dictionaries or translation models. Experiments on ByT5-small and Qwen2-1.5B show that MGDA substantially improves Manchu text generation performance: BLEU-4/ROUGE-L increases from 2.03/2.59 to 17.60/42.70 for ByT5, and from 1.98/6.42 to 14.12/41.49 for Qwen. Further ablation studies demonstrate the complementarity of the three augmentation granularities and suggest potential benefits of byte-level modeling in this experimental setting.