Welcome to xrenner’s documentation!¶
xrenner (eXternally configurable REference and Non Named Entity Recognizer) is a highly configurable, language independent coreferencer and (non) named entity recognizer, written in Python. It is built to analyze natural language input and recognize what kind of entities (people, places, objects, abstractions...) appear in them and how they are referred to (recognize that Grace Murray Hopper can be the same person as she in context).
You can find some more information about the system in the following paper. This is also the paper to cite if you use xrenner in publications:
Zeldes, Amir and Zhang, Shuo (2016) When Annotation Schemes Change Rules Help: A Configurable Approach to Coreference Resolution beyond OntoNotes. In: Proceedings of the NAACL2016 Workshop on Coreference Resolution Beyond OntoNotes (CORBON). San Diego, CA, 92-101.