Code relative to the participation of the HULAT-UC3M team in the CANTEMIST-CANcer TExt Mining Shared Task – tumor named entity recognition.
We used a deep learning architecture for the identification of named tumor morphology entities. The architecture consists of convolutional and bidirectional Long Short-Term Memory layers and a final layer based on ConditionalRandom Field.
The developed code is here
During our participation, we developed a dictionary with the National Cancer Institute's dictionary terminology to be used together with Meaning Cloud. You can find it here.