Definitional Question Answering Using Text Triplets

Abstract

Definitional question answering deals with answering questions of the type “Who is X” and “What is X.” The techniques used in the literature extract long sentences that may not only give irrelevant facts, but also pose difficulty in evaluating the performance of the system. In this paper, we propose a technique that uses text triplets. We further choose relevant triplets based on a manually built list of terms that are found in definitions in general. The selected triplets give simple, short, and precise definitions of the target. We also show that evaluation becomes easy.