Modeling Unrestricted Coreference in OntoNotes

The CoNLL-2011 shared task involved predicting coreference using OntoNotes data. Resources in this field have tended to be limited to noun phrase coreference, often on a restricted set of entities, such as ACE entities. OntoNotes provides a large-scale corpus of general anaphoric coreference not restricted to noun phrases or to a specified set of entity types. OntoNotes also provides additional layers of integrated annotation, capturing additional shallow semantic structure. This paper briefly describes the OntoNotes annotation (coreference and other layers) and then describes the parameters of the shared task including the format, pre-processing information, and evaluation criteria, and presents and discusses the results achieved by the participating systems. Having a standard test set and evaluation parameters, all based on a new resource that provides multiple integrated annotation layers (parses, semantic roles, word senses, named entities and coreference) that could support joint models, should help to energize ongoing research in the task of entity and event coreference.