New Information Distance Measure and Its Application in Question Answering System

In a question answering (QA) system, the fundamental problem is how to measure the distance between a question and an answer, hence ranking different answers. We demonstrate that such a distance can be precisely and mathematically defined. Not only such a definition is possible, it is actually provably better than any other feasible definitions. Not only such an ultimate definition is possible, but also it can be conveniently and fruitfully applied to construct a QA system. We have built such a system — QUANTA. Extensive experiments are conducted to justify the new theory. Electronic supplementary material The online version of this article (doi:) contains supplementary material, which is available to authorized users. This work is supported by the National Natural Science Foundation of China under Grant Nos. 60572084 and 60621062.