Metraipolis › archive › dc_99e4faba2e63

HERIT: Enabling Global Access to Hanja-to-English Historical Translation by Mitigating Temporal Bias — arXiv:2611.04949

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.04949
License (as archived): CC0-1.0
Archived: 2026-11-04T21:43:39.612Z
SHA-256 of the archived text: 85b78b52e82e1dd151cc0bd94e23ac3ce48404d9eb0f6c3fb85c728f00d4241c
Stable URL of this page: https://metraipolis.com/documento/dc_99e4faba2e63

How to cite

HERIT: Enabling Global Access to Hanja-to-English Historical Translation by Mitigating Temporal Bias — arXiv:2611.04949 — arXiv (en), https://arxiv.org/abs/2611.04949 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_99e4faba2e63 (Metraipolis archive dc_99e4faba2e63, sha256 85b78b52e82e1dd151cc0bd94e23ac3ce48404d9eb0f6c3fb85c728f00d4241c)

BibTeX

@misc{dc99e4faba2e63,
  title = {HERIT: Enabling Global Access to Hanja-to-English Historical Translation by Mitigating Temporal Bias — arXiv:2611.04949},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04949},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_99e4faba2e63; sha256 85b78b52e82e1dd151cc0bd94e23ac3ce48404d9eb0f6c3fb85c728f00d4241c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04949. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2611.04949 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-04T21:36:04.437Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).