Mention classification lays between Named Entity Recognition and Entity Linking. - It provides much more detailed information about an object than NER does. - At the same time, it does not require storing and maintaining any knowledge base with known objects. - The Classifier able to work with absolutely new objects never appeared in the train set. - The neural net is able to look at up to five mentions simultaneously. It combines evidence more efficient than it could be achieved by averaging individual predictions.
- Support for other languages - Support for other entities
Don't forget to add the tag @generall in your comments.