Knet implementation for the Neural End-to-End Learning for Computational Argumentation Mining paper.
Computational argumentation mining (AM) deals with finding argumentation structures in text. This involves several subtasks, such as:
- Separating argumentative units from non-argumentative units, also called ‘component segmentation’.
- Classifying argument components into classes such as “Premise” or “Claim”.
- Finding relations between argument components.
- Classifying relations into classes such as “Support” or “Attack”