Low-resource Information Extraction with the European Clinical Case Corpus
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908285111631872 |
|---|---|
| author | Ghosh, Soumitra Altuna, Begona Farzi, Saeed Ferrazzi, Pietro Lavelli, Alberto Mezzanotte, Giulia Speranza, Manuela Magnini, Bernardo |
| author_facet | Ghosh, Soumitra Altuna, Begona Farzi, Saeed Ferrazzi, Pietro Lavelli, Alberto Mezzanotte, Giulia Speranza, Manuela Magnini, Bernardo |
| contents | We present E3C-3.0, a multilingual dataset in the medical domain, comprising clinical cases annotated with diseases and test-result relations. The dataset includes both native texts in five languages (English, French, Italian, Spanish and Basque) and texts translated and projected from the English source into five target languages (Greek, Italian, Polish, Slovak, and Slovenian). A semi-automatic approach has been implemented, including automatic annotation projection based on Large Language Models (LLMs) and human revision. We present several experiments showing that current state-of-the-art LLMs can benefit from being fine-tuned on the E3C-3.0 dataset. We also show that transfer learning in different languages is very effective, mitigating the scarcity of data. Finally, we compare performance both on native data and on projected data. We release the data at https://huggingface.co/collections/NLP-FBK/e3c-projected-676a7d6221608d60e4e9fd89 . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_20568 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Low-resource Information Extraction with the European Clinical Case Corpus Ghosh, Soumitra Altuna, Begona Farzi, Saeed Ferrazzi, Pietro Lavelli, Alberto Mezzanotte, Giulia Speranza, Manuela Magnini, Bernardo Computation and Language We present E3C-3.0, a multilingual dataset in the medical domain, comprising clinical cases annotated with diseases and test-result relations. The dataset includes both native texts in five languages (English, French, Italian, Spanish and Basque) and texts translated and projected from the English source into five target languages (Greek, Italian, Polish, Slovak, and Slovenian). A semi-automatic approach has been implemented, including automatic annotation projection based on Large Language Models (LLMs) and human revision. We present several experiments showing that current state-of-the-art LLMs can benefit from being fine-tuned on the E3C-3.0 dataset. We also show that transfer learning in different languages is very effective, mitigating the scarcity of data. Finally, we compare performance both on native data and on projected data. We release the data at https://huggingface.co/collections/NLP-FBK/e3c-projected-676a7d6221608d60e4e9fd89 . |
| title | Low-resource Information Extraction with the European Clinical Case Corpus |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2503.20568 |