Liuliu writeup of Cohen 2003

This is a review of Cohen_2003_a_comparison_of_string_distance_metrics_for_name_matching_tasks by user:Liuliu.

This paper compares several string distance metrics: token-based distance metrics, edit distance based methods and their proposed hybrid distance method(SoftTFIDF) which combines the above two schemes. Results show that the hybrid approach achieves a better performance on both matching and clustering tasks. Further, a hybrid approach which combines distance metrics by using SVM is evaluated and achieves a better performance.