In this paper, we introduce the task of predicting severity of age-restricted aspects of movie content based solely on the dialogue script. We first investigate categorizing the ordinal severity of movies on 5 aspects: Sex, Violence, Profanity, Substance consumption, and Frightening scenes. The problem is handled using a siamese network-based multitask framework which concurrently improves the interpretability of the predictions. The experimental results show that our method outperforms the previous state-of-the-art model and provides useful information to interpret model predictions. The proposed dataset and source code are publicly available at our GitHub repository.

翻译：在本文中,我们介绍一项任务,即完全根据对话文字预测电影内容受年龄限制的方面的严重性;我们首先调查5个方面对电影的典型严重性进行分类:性、暴力、专业性、物质消费和惊吓场景;用一个基于网络的尖锐网络多任务框架来处理问题,同时改善预测的可解释性。实验结果显示,我们的方法优于以前的最先进的模型,为解释模型预测提供了有用的信息。提议的数据集和源代码在我们的GitHub储存库中公开提供。