Event causality extraction is one of the important components of information extraction tasks,and it is also a hot and difficult issue in current natural language processing research.Event causality extraction studies the potential relationship be-tween events in the text,which is conducive to in-depth analysis of the causes and trends of the development of events,and has been widely used in many fields.According to the different methods of event causality extraction,it can be divided into three catego-ries:based on template matching,based on machine learning and based on deep learning.This paper introduces the task of event causality extraction,and reviews the development of event causality extraction.Then,three categories of methods for event causality extraction and related pre-trained language models are introduced,and the future development trends are summarized and prospect-ed.
natural language processingcausal relationship extractionmachine learningdeep learningneural network
国家科技期刊平台
NSTL
万方数据
