Cross-lingual Natural Language Processing on Limited Annotated Case/Radiology Reports in English and Japanese: Insights from the Real-MedNLP Workshop
Most systems adopt medical-domain-specific pretrained language models using data augmentation methods. Despite the challenge of limited corpus size in Tasks 1 and 2, recent approaches are promising because the partial match scores reached ∼0.8-0.9 F1-scores. Task 3 applications revealed that the different availabilities of external language resources affected the performance per language.
Authors
- Shuntaro Yada (ORCID: https://orcid.org/0000-0002-6209-1054)
- Eiji Aramaki (ORCID: https://orcid.org/0000-0003-0201-3609)
- Shoko Wakamiya (ORCID: https://orcid.org/0000-0002-9371-1340)
- Yuta Nakamura (ORCID: https://orcid.org/0000-0001-6962-6704)
Institutions
- University of Tokyo Hospital (JP)
- Nara Institute of Science and Technology (JP)
Publication Details
- Journal
- Methods of Information in Medicine
- Published
- 2024-08-29
- DOI
- https://doi.org/10.1055/a-2405-2489
- Citations
- 6
- Primary Topic
- Topic Modeling
- Type
- article
- Field-Weighted Citation Impact
- 2.08
Funders
- Ministry of Health, Labour and Welfare
- Japan Science and Technology Agency