Extracting answers from causal mechanisms in a medical document

The aim of this paper is to approach causal questions in medical documents eventually recovered from a search engine. Causal questions par excellence are what, how and why-questions. The ‘pyramid of questions’ shows this. At the top, why-questions are the prototype of causal questions. Usually why-questions are related to scientific explanations. Although cover law explanation is characteristically of physical sciences, it is less common in biological or medical knowledge. In medicine, laws applied to all cases are rare. It seems that doctors express their knowledge using mechanisms instead of natural laws. In this paper we will approach causal questions with the aim of: (1) answering what-questions as identifying the cause of an effect; (2) answering how-questions as selecting an appropriate part of a mechanism that relates pairs of cause-effect (3) answering why-questions as identifying central causes in the mechanism which answer how-questions. To automatically get answers to why-questions, we hypothesize that the deepest knowledge associated to them can be obtained from the central nodes of the graph that schematizes the mechanism. Our contribution is concerned with medical question answering systems, even though our approach does not address how to retrieve medical documents as a primary answer to a question, but how to extract relevant causal answers from a given document previously extracted by using a search engine. Thus, our paper deals with the automatic detection and extraction of causal relations from medical documents.

keywords: Causal questions, Mechanisms, Imperfect causality, Answering causal questions