Learning Causal Bayesian Networks from Text

Learning Causal Bayesian Networks from Text Farhad Moghimifar, Afshin Rahimi, Mahsa Baktashmotlagh and Xue Li The School of ITEE The University of Queensland, Australia {f.moghimifar,a.rahimi,m.baktashmotlagh}@uq.edu.au xueli@itee.uq.edu.au Abstract Causal relationships form the basis for reason- ing and decision-making in Artificial Intelli- gence systems. To exploit the large volume of textual data available today, the automatic discovery of causal relationships from text has emerged as a significant challenge in recent years. Existing approaches in this realm are limited to the extraction of low-level relations among individual events. To overcome the lim- itations of the existing approaches, in this pa- per, we propose a method for automatic infer- ence of causal relationships from human writ- ten language at conceptual level. To this end, we leverage the characteristics of hierarchy of concepts and linguistic variables created from text, and represent the extracted causal rela- tionships in the form of a Causal Bayesian Network. Our experiments demonstrate supe- riority of our approach over the existing ap- proaches in inferring complex causal reason- ing from the text. 1 Introduction Causation is a powerful psychological tool for human to choreograph his surrounding environ- ment into a mental model, and use it for reason- ing and decision-making. However, inability to identify causality is known to be one of the draw- backs of current Artificial Intelligence (AI) systems (Lake et al., 2015). Extraction of causal relations from text is necessity in many NLP tasks such as question answering and textual inference, and has attracted a considerable research in recent years (Wood-Doughty et al., 2018; Zhao et al., 2018, 2017; Ning et al., 2018; Rojas-Carulla et al., 2017). However, the state-of-the-art methods are limited to the identification of causal relations between low-level individual events (Dunietz et al., 2017; Hidey and McKeown, 2016; Mirza and Tonelli, 2016) and fail to capture such relationships at con- ceptual level. Furthermore, relying on linguistic features limits the identification of causal relations to those whose cause and effect are located in the same sentence or in consecutive sentences. In this paper, we propose a method for extract- ing concepts and their underlying causal relations from written language. Furthermore, to leverage the extracted causal information, we represent the causal knowledge in the form of a Causal Bayesian Network (CBN). Having this tool enables answer- ing complex causal and counter-factual questions, such as: How psychotherapy can affect the pa- tient’s emotion?, or What would happen if instead of medicine X, medicine Y was prescribed? The contribution of this paper is three-fold. Firstly, we focus on identifying causal relation be- tween concepts (e.g. physical activity and health). Secondly, We propose a novel method to represent the extracted causal knowledge in the form of a Causal Bayesian Network, enabling easy incorpora- tion of this invaluable knowledge into downstream NLP tasks. Thirdly, we release PSYCAUS dataset which can be used to evaluate causal relation ex- traction models in the domain of psychology 1. In addition, our proposed method identifies causality between concepts independent of their locations in text, and is …

Content truncated to 500 words