NestDE: generic parameters tuning for automatic story segmentation

Abstract

Parameters tuning is a crucial task in automatic story segmentation. For most previous story segmentation methods, however, the parameters were simply derived from empirical tuning, which may indeed harm the fairness of the evaluation, or even misguide the conclusion. In this paper, we present a general parameters tuning approach, namely nested differential evolution. As a practical general-purpose parameters tuner, our approach itself is parameters-robust and is generic enough to optimize the most usual types of parameters for the given corpus and evaluation criterion. Besides, our approach is able to cooperate with empirical tuning and jointly produce better parameters based on the prior knowledge of experienced users. Extensive experiments on synthetic challenging quadratic pseudo-Boolean optimization and real-world story segmentation tasks validate the superior performance of our approach over traditional empirical tuning and other generic optimizers, such as simulated annealing and classical differential evolution.