Conference Proceedings
Impact of Corpus Diversity and Complexity on NER Performance
T Shmanina, I Zukerman, AJ Jimeno Yepes, L Cavedon, CM Verspoor
ACL Anthology | Published : 2013
Abstract
We describe a cross-corpora evaluation of disease mention recognition for two annotated biomedical corpora: the Human Variome Project Corpus and the Arizona Disease Corpus. Our analysis of the performance of a state-of-the-art NER tool in terms of the characteristics and annotation schema of these corpora shows that these factors significantly affect performance.