This repository contains the data and code created under the project NLP4Rare-cm-uc3m. Its main objective is to cover the main relevant NLP tasks on a customised corpus oriented towards rare diseases and their clinical manifestations: the RareDis corpus.

A description of the corpus can be found in:

The RareDis corpus: a corpus annotated with rare diseases, their signs and symptoms Claudia Martínez-deMiguel, Isabel Segura-Bedmar, Esteban Chacón-Solano, Sara Guerrero-Aspizua

The corpus can be accessed in its original form via the following repository.

The results obtained for NER task can be found in:

Exploring deep learning methods for recognizing rare diseases and their clinical manifestations from texts Isabel Segura-Bedmar, David Camino-Perdones, Sara Guerrero-Aspizua

---

Project NLP4Rare-cm-uc3m

---