A Logic Based Approach to Answering Questions about Alternatives in DIY Domains

Abstract

Many question answering systems have primarily focused on factoid questions. These systems require the answers to be explicitly stored in a knowledge base (KB) but due to this requirement, they fail to answer many questions for which the answers cannot be pre-formulated. This paper presents a question answering system which aims at answering nonfactoid questions in the DIY domain using logic-based reasoning. Specifically, the system uses Answer Set Programming to derive an answer by combining various types of knowledge such as domain and commonsense knowledge. We showcase the system by answering one specific type of questions — questions about alternatives. The evaluation result shows that our logic-based reasoning together with the KB (constructed from texts using Information Extraction) significantly improves the user experience.