# Towards Effective Ancient Chinese Translation: Dataset, Model, and Evaluation

arXiv: https://arxiv.org/abs/2308.00240 · HTML: https://mlsanity.com/paper/2308.00240/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 34 references that are in the map.
- First posted on arXiv 1 Aug 2023.

## Builds on (most cited first, 19 of 19)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [Cross-lingual Language Model Pretraining](https://mlsanity.com/paper/1901.07291/) (2019)
- [Multilingual Denoising Pre-training for Neural Machine Translation](https://mlsanity.com/paper/2001.08210/) (2020)
- [CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation](https://mlsanity.com/paper/2109.05729/) (2021)
- [Pre-training Multilingual Neural Machine Translation by Leveraging Alignment Information](https://mlsanity.com/paper/2010.03142/) (2020)
- [DeltaLM: Encoder-Decoder Pre-training for Language Generation and Translation by Augmenting Pretrained Multilingual Encoders](https://mlsanity.com/paper/2106.13736/) (2021)
- [MT6: Multilingual Pretrained Text-to-Text Transformer with Translation Pairs](https://mlsanity.com/paper/2104.08692/) (2021)
- [AnchiBERT: A Pre-Trained Model for Ancient ChineseLanguage Understanding and Generation](https://mlsanity.com/paper/2009.11473/) (2020)
- [Universal Conditional Masked Language Pre-training for Neural Machine Translation](https://mlsanity.com/paper/2203.09210/) (2022)
- [Time-Aware Ancient Chinese Text Translation and Inference](https://mlsanity.com/paper/2107.03179/) (2021)
- [Ancient-Modern Chinese Translation with a Large Training Dataset](https://mlsanity.com/paper/1808.03738/) (2018)
- [TextBox 2.0: A Text Generation Library with Pre-trained Language Models](https://mlsanity.com/paper/2212.13005/) (2022)

## Built on by (most cited first, 7 of 7)

- [AC-EVAL: Evaluating Ancient Chinese Language Understanding in Large Language Models](https://mlsanity.com/paper/2403.06574/) (2024)
- [What is the best model? Application-driven Evaluation for Large Language Models](https://mlsanity.com/paper/2406.10307/) (2024)
- [F`ux`i: A Benchmark for Evaluating Language Models on Ancient Chinese Text Understanding and Generation](https://mlsanity.com/paper/2503.15837/) (2025)
- [InteChar: A Unified Oracle Bone Character List for Ancient Chinese Language Modeling](https://mlsanity.com/paper/2508.15791/) (2025)
- [Exploring the Capabilities of ChatGPT in Ancient Chinese Translation and Person Name Recognition](https://mlsanity.com/paper/2312.15304/) (2023)
- [CalliReader: Contextualizing Chinese Calligraphy via an Embedding-Aligned Vision-Language Model](https://mlsanity.com/paper/2503.06472/) (2025)
- [Efficiently Building a Domain-Specific Large Language Model from Scratch: A Case Study of a Classical Chinese Large Language Model](https://mlsanity.com/paper/2505.11810/) (2025)

## Abstract (arXiv)

Interpreting ancient Chinese has been the key to comprehending vast Chinese literature, tradition, and civilization. In this paper, we propose Erya for ancient Chinese translation. From a dataset perspective, we collect, clean, and classify ancient Chinese materials from various sources, forming the most extensive ancient Chinese resource to date. From a model perspective, we devise Erya training method oriented towards ancient Chinese. We design two jointly-working tasks: disyllabic aligned substitution (DAS) and dual masked language model (DMLM). From an evaluation perspective, we build a benchmark to judge ancient Chinese translation quality in different scenarios and evaluate the ancient Chinese translation capacities of various existing models. Our model exhibits remarkable zero-shot performance across five domains, with over +12.0 BLEU against GPT-3.5 models and better human evaluation results than ERNIE Bot. Subsequent fine-tuning further shows the superior transfer capability of Erya model with +6.2 BLEU gain. We release all the above-mentioned resources at https://github.com/RUCAIBox/Erya.