Abstract
We propose a transfer learning method that adapts a high-resource English clinical NER model to low-resource languages and domains using only small amounts of in-domain annotated data. Our approach involves translating in-domain datasets to English, fine-tuning the English model on the translated data, and then transferring it to the target language/domain. Experiments on Spanish, French, and conversational clinical text datasets show accuracy gains over models trained on target data alone. Our method achieves state-of-the-art performance and can enable clinical NLP in more languages and modalities with limited resources.- Anthology ID:
- 2023.clinicalnlp-1.53
- Volume:
- Proceedings of the 5th Clinical Natural Language Processing Workshop
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Tristan Naumann, Asma Ben Abacha, Steven Bethard, Kirk Roberts, Anna Rumshisky
- Venue:
- ClinicalNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 514–518
- Language:
- URL:
- https://aclanthology.org/2023.clinicalnlp-1.53
- DOI:
- 10.18653/v1/2023.clinicalnlp-1.53
- Cite (ACL):
- Nevasini Sasikumar and Krishna Sri Ipsit Mantri. 2023. Transfer Learning for Low-Resource Clinical Named Entity Recognition. In Proceedings of the 5th Clinical Natural Language Processing Workshop, pages 514–518, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Transfer Learning for Low-Resource Clinical Named Entity Recognition (Sasikumar & Mantri, ClinicalNLP 2023)
- PDF:
- https://preview.aclanthology.org/corrections-2024-04/2023.clinicalnlp-1.53.pdf