A new approach to zone identification based on considering features with high semantic richness

Abstract

In this paper, we propose a new approach to zone identification based on considering features with high semantic richness such as specialized names and mode of verbs belonging to a text's domain of interest and besides that mode of verbs, while taking into account features with less computational cost compared to those of conventional methods. Out of the scenarios of selecting features for identifying a zone based on classifying the sentences in a text, we came to notice that in the scenario where specialized names and mode of verbs are taken into account together with reduced versions of conventional features including history, an accuracy rate of 61% (resp. 81%) is obtained which is higher than those belonging to both Liakata's and Fisas's approach. Also, to have a genuine comparison, both Liakata's and Fisas's corpuses are used in our experiments. Such accuracy is obtained at the place where less computational cost is taken for extracting the features.