NIST logo

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

NIST Authors in Bold

Author(s): S. Strassle; Mark A. Przybocki; Kay Peterson; Zhiyi Song; Kazuaki Maeda;
Title: Linguistic Resources and Evaluation Techniques for Evaluation of Cross-Document Automatic Content Extraction
Published: August 27, 2008
Abstract: 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.
Conference: The sixth international conference on Language Resources and Evaluation, LREC 2008
Pages: 5 pp.
Location: Marrakech, MO
Dates: May 28-30, 2008
Keywords: automatic content extraction; cross-document
Research Areas: Imaging