Preprocessing of normative documents for interactive question answering

Abstract

Every larger organisation must establish a set of normative documents to control its processes and describe solutions to common problems. These documents are usually formally written and hard to read. This leads to the necessity off different customer services. Nowadays, a lot of companies are developing chatbots to automate first-line customer support. If a company does not have a large question–answer dataset to build a chatbot, the answers can be automatically answered directly from the documents. However, we found that the automatic answering usually does not work well on the normative documents. In this paper, we describe a novel method for preprocessing of normative documents in order to use them for such automatic question answering. Our method efficiently exploits the strict document structure that is typical for normative documents. The method enabled us to increase the recall from 35% to 84% (for paragraph-size answers) on selected normative documents from university and bank domains.