On semi-automated extraction of causal networks from raw text

Abstract

A rule-based framework, named SCANER (Semi-automated CAusal Network Extraction from Raw text) is presented. SCANER converts raw text into causal networks using a set of natural language processing rules. The raw textual data that contains useful information for informing future decisions and developing strategies in various critical domains must be converted into useful, understandable models. However, building such models manually from raw text is a labor-intensive and time-consuming process and needs to be automated. The automated extraction of causality from raw text, however, has its own set of challenges due to the linguistic complexity and ambiguity of the texts. It can also be argued that for complicated scenarios and critical domains subject matter experts cannot rely solely on such automatically generated models without sound reasoning to support them. This implies the need for a semi-automated human-in-the-loop approach. This research, therefore, is focused on combining the strengths of both manual and automated approaches and on developing a framework for a rule-based semi-automated approach to generate causal networks from raw text. SCANER is evaluated on three collections of raw text from political, food insecurity, and medical domains using F-Score as the evaluation metric. The ground truth for the causal links is generated after incorporating feedback from a group of three human judges. A comparative analysis with Eidos, an open-source causality extraction system, demonstrates the advantages of SCANER in generating dense and accurate causal networks from the raw text.