# Coreference Resolution Co-reference Resolution (CR) is the task of deciding whether two entity mentions refer to the same instance or not. For example in: > Joe Biden appeared at the event at 8pm. The president was wearing a Louis Vuitton Tuxedo. The objective is to identify that Joe Biden and The president are the same entity. Coreference Detection is related to [Relationship Extraction (RE)](https://wiki.jamesravey.me/books/ai-and-ml/page/relationship-extraction "Relationship Extraction") - in fact you could even say that CR is a special case of RE in the sense that we are interested in the special relationship between entity mentions when they both refer to the same entity. ### In-Document Coreference Resolution This is the "normal" CR case in which you're trying to resolve mentions of entities within the same document e.g. a single news article. #### Approaches - **2022-10-23** [A recent blog post ](https://explosion.ai/blog/coref)from explosion / spaCy shows how they have implemented end-to-end CR in their excellent NLP pipeline but as of writing they do not provide a trained model and they require you to have a copy of the Ontonotes dataset. ### Cross-Document Coreference Resolution Cross-Document Coreference Resolution (CDCR) is when you try to link named entity references across multiple input documents. A use case might be identifying that a number of news articles do actually refer to the same person (e.g. "Joe Biden", "The President"). CDCR is challenging because there are so many possible entities and thus O(n2) comparisons to make between candidates. #### Approaches - In 2021 [we proposed CD^2CR](https://arxiv.org/abs/2101.12637) - a CDCR approach across documents and domains that allows us to match mentions of people, places, technologies etc across scientific papers and news articles that discuss them.