Automatic Content Extraction 2008 Evaluation Plan ( ACE 08 ) Assessment of Detection and Recognition of Entities and Relations Within and Across Documents

The objective of the Automatic Content Extraction (ACE) series of evaluations has been to develop human language understanding technologies that provide automatic detection and recognition of key information about real-world entities, relations, and events in source language text, and to convert that information into a structured form, which can be used by follow-on processes, such as classification, filtering and selection, database update, relationship display, and many others.