Metraipolis › archive › dc_acbd9c9ae4eb

Cross-Lingual Clinical Annotation Projection as Constrained Text Generation: A Six-Language Study — arXiv:2609.11450

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.11450
License (as archived)
CC0-1.0
Archived
2026-10-16T05:27:04.469Z
SHA-256 of the archived text
c9ab8ed281e7d905c4b39d32eea4da193e78adec0048dcc690f29012c7392a0d
Stable URL of this page
https://metraipolis.com/documento/dc_acbd9c9ae4eb

How to cite

Cross-Lingual Clinical Annotation Projection as Constrained Text Generation: A Six-Language Study — arXiv:2609.11450 — arXiv (en), https://arxiv.org/abs/2609.11450 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_acbd9c9ae4eb (Metraipolis archive dc_acbd9c9ae4eb, sha256 c9ab8ed281e7d905c4b39d32eea4da193e78adec0048dcc690f29012c7392a0d)
BibTeX
@misc{dcacbd9c9ae4eb,
  title = {Cross-Lingual Clinical Annotation Projection as Constrained Text Generation: A Six-Language Study — arXiv:2609.11450},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.11450},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_acbd9c9ae4eb; sha256 c9ab8ed281e7d905c4b39d32eea4da193e78adec0048dcc690f29012c7392a0d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11450. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Background: To determine whether cross-lingual clinical annotation projection can be formulated as a text-preserving, document-level generative task that produces verifiable character-level annotations for multilingual clinical corpus construction, and to characterize its robustness and computational trade-offs relative to candidate-based projection pipelines. Methods: We developed a constrained LLM projection workflow that inserts entity tags directly into immutable target-language text, followed by deterministic validation and character-offset reconstruction. We evaluated it alongside supervised candidate-span projection and hybrid ML-LLM refinement for transferring Spanish Disease, Symptom, and Procedure annotations into six languages. Evaluation used MultiClinAI gold standard with strict span matching and character-overlap F1 Results: Direct LLM projection achieved the strongest and most consistent performance. GLM 5.2 obtained a mean Strict F1 of 0.9201 across 18 language-entity combinations, while locally deployable Gemma4:31B achieved 0.9133. The best LLM configuration improved Strict F1 over the previous state of the art in all 18 settings, by 0.0564-0.1512, yielding 55,416 grounded mentions with reconstructed offsets. Conclusions: Direct LLM-based projection enables high-quality multilingual clinical annotation transfer and provides a practical approach for extending clinical NLP resources to languages with fewer annotated datasets and language-specific tools. Combined with local inference and deterministic validation, it can substantially reduce expert time and cost for multilingual clinical corpus construction.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.11450 — 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 2026-10-16T05:17:52.169Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).