Improving Arabic morphological analyzers benchmark

Abstract The various tools dedicated to Arabic natural language processing have undergone significant development during recent years. Among these tools, Arabic morphological analyzers are of great importance because they are often used within other projects that are more advanced such as syntactic parsers, search engines, machine translation systems, etc. Thus, researchers are forced to make a decision concerning which morphological analyzer to use in their research projects, and this task is very difficult since there are many criteria to take into account. In order to facilitate this choice, we considered the problem of benchmarking morphological analyzers in a previous work by proposing a solution that allows returning a set of metrics of each analyzer that are: accuracy, precision, recall, F-measure and the execution time. In this article, we present two new major improvements to our solution: the establishment of the first version of our corpus that is dedicated to the evaluation of morphological analyzers, as well as the introduction of a new metric, which combines all metrics related to results as well as the execution time of the analyzers.