HERIT: Enabling Global Access to Hanja-to-English Historical Translation by Mitigating Temporal Bias

Abstract:Historical archives are invaluable for multidisciplinary research but remain inaccessible globally due to severe language barriers. While manual translation is prohibitively expensive and time-consuming, simply applying existing machine translation models is inadequate due to unique linguistic nuances and the temporal bias inherent in scarce human-labeled corpora. To address these challenges, we propose HERIT, a systematic domain-adaptation pipeline that leverages retrieval-augmented generation (RAG) to generate high-quality pseudo-labeled data from abundant Hanja-Korean corpora. This approach substantially expands the training dataset, mitigating both data scarcity and temporal overfitting across different historical periods. Extensive automated and human evaluations demonstrate that HERIT consistently outperforms baselines. Finally, we translate previously untranslated portions of the archives using our model, thereby enabling global access to these resources for researchers.

Accepted to Findings of EMNLP 2026. 17 pages, 10 figures, 11 tables

Computation and Language (cs.CL)

arXiv:2611.04949 [cs.CL]

(or arXiv:2611.04949v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2611.04949 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

https://doi.org/10.18653/2026.findings-emnlp.2326 Focus to learn more DOI(s) linking to related resources

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.