Linguistic Resources and Evaluation Techniques for Evaluation of Cross-Document Automatic Content Extraction

The NIST Automatic Content Extraction (ACE) Evaluation expands its focus in 2008 to encompass the challenge of cross-document and cross-language global integration and reconciliation of information. While past ACE evaluations were limited to local (within-document) detection and disambiguation of entities, relations and events, the current evaluation adds global (cross-document and cross-language) entity disambiguation tasks for Arabic and English. This paper presents the 2008 ACE XDoc evaluation task and associated infrastructure. We describe the creation of development and test data to support the evaluation, focusing on new approaches required in data selection, annotation task definition and annotation software; and we conclude with a discussion of the metrics developed to support the evaluation.