Coreference resolution (i.e., resolving coreferences) is a task of clustering (i.e., matching) mentions that refer to the same entity. A mention represents a reference to an underlying entity that is mentioned in a text as a noun entity, using a pronoun, or is implicitly contained in a verb form (i.e., Slovene language specific). The result of the task are clusters of mentions, where each cluster represents one entity. Coreference resolution algorithms need to be able to process the whole document at once as they need to understand the discourse at a higher semantic level - pragmatics, in order to achieve good results. In addition to name entity recognition and link extraction, this is a more challenging information extraction task.
Web service should be used for demonstration purposes only, and is limited by the number of requests per time unit and input length. To use the service within your applications, please download results of the projects, available in the Clarin.si repository.
Tool available at: https://github.com/RSDO-DS3/SloCOREF