
Edison is an NLP data representation and feature extraction framework that can be used to store several annotations of text. Examples of annotations include named entities, parse trees, semantic role labels, etc Edison represents all these as a graph, where nodes are groups of tokens called Constituents and the labeled edges between the nodes are called Relations.
Edison has been used to implement several of our group's large NLP software, including the Semantic Role Labeler, the NER and the Wikifier.
For further details and examples, please click download above.