Research On Ethical Behavior Discrimination Based On Deep Learning

With the broader applications of Artificial Intelligence(AI),their ethical and moral issues have attracted more and more concerns.How to develop an AI system that complies with human values and ethical norms from the perspective of technology realization,namely,ethical aligned AI design,is one of the important issues that need to be solved urgently.The ethical and moral discrimination based on machine learning is a beneficial exploration in this aspect.Social news data has rich content and knowledge of ethics and morality,which provides the possibility for the training data development of machine learning.In this paper,we investigate on deep learning based ethical behavior discriminative methods.The research is carried out in terms of ethical behavior discrimination and more fine-grained ethical behavior term extraction,purpose relation inference,and ethical polarity discrimination.We propose a model for ethical behavior discrimination based on social news datasets,followed by a new natural language processing task,behavior-based ethical understanding,for mining purposive relationships and ethical polarity of specific behaviors from social news.The specific research content are as follows:(1)In this paper,we constructs a social news dataset with ethics and morality of human behavior,which is attached to law and code of conduct dataset for machine learning training and testing.The ethical behavior discrimination model ERNIE-CNN based on Enhanced Language Representation of Information Entities(ERNIE)and Convolutional Neural Network(CNN),is developed to extract ethical discriminations about behavior by calculating semantic similarity based on the vector representation of words.The experimental results show that the proposed model has better performance than the baseline models.(2)A new natural language processing task,behavior-based ethical understanding(BEU),is proposed in this paper for mining the purpose relation(s)and ethical polarity of a specific behavior from the social news.It contains three subtasks: behavior term extraction(BTE)to extracts behavior terms,purpose relation inference(PRI)to identifies purposive relations among behaviors,and polarity discrimination(PD)to predicts the ethical polarities of behaviors,respectively.To perform this task,we constructed a Chinese BEU dataset,named FG-ETHICS.(3)A three-stage framework,BEU-BERT,based on the pre-trained language model BERT is designed,and downstream models are deliberately designed for the three subtasks.Experimental results show that the proposed framework achieves the best performance from the BTE and PD tasks,and achieves a promising performance of 75% on the PRI task.