Optical Memory and Neural Networks ( IF 1.0 ) Pub Date : 2021-07-02 , DOI: 10.3103/s1060992x21020077 Yongheng Chen 1 , Chunyan Yin 2 , Wanli Zuo 3
Abstract
Rumor detection and stance classification are specialized areas in the field of Information Retrieval and Natural Language Processing. Judging the stances of public response is viewed as an important preceding step of rumor veracity prediction. In this paper we develop a reinforcement learning-based multi-task learning for rumor early detection (RL_MT_RED), which formulates the closely correlated rumor detection and stance classification problems as a multi-task learning and jointly learn them. Otherwise, in order to realize the early rumour detection, RL_MT_RED integrates reinforcement learning to control multi-task learning, and realizes to dynamically set credible checkpoint. The experimental results indicate that our proposed method is superior to the traditional methods.
中文翻译:
用于立场和早期谣言检测的多任务学习
摘要
谣言检测和立场分类是信息检索和自然语言处理领域的专业领域。判断公众反应的立场被视为谣言真实性预测的重要步骤。在本文中,我们开发了一种基于强化学习的谣言早期检测多任务学习(RL_MT_RED),它将密切相关的谣言检测和立场分类问题制定为多任务学习并共同学习。否则,为了实现早期谣言检测,RL_MT_RED 集成了强化学习来控制多任务学习,并实现动态设置可信检查点。实验结果表明,我们提出的方法优于传统方法。