In order for a system to answer a question, it needs to be able to extract the answer, usually found as a fact, from relevant text containing it. In this paper we describe a method of classifying facts (information) into categories or levels; where each level signifies a different degree of difficulty of extracting the fact from a piece of text containing it. We proceed to show how this is relevant to evaluating the complexity of a question-answering task.
展开▼
