Using a Distributional Semantic Vector Space with a Knowledge Base for Reasoning in Uncertain Conditions
This addresses the problem of limited reasoning in uncertain conditions for AI systems using knowledge bases, representing an incremental improvement by combining existing methods.
The paper tackles the inflexibility and incompleteness of commonsense knowledge bases (KB) by introducing Displacer, a system that integrates a KB with a word2vec distributional semantic vector space (DSVS) to answer queries not originally contained in the KB, providing approximate answers where the KB alone would fail.
The inherent inflexibility and incompleteness of commonsense knowledge bases (KB) has limited their usefulness. We describe a system called Displacer for performing KB queries extended with the analogical capabilities of the word2vec distributional semantic vector space (DSVS). This allows the system to answer queries with information which was not contained in the original KB in any form. By performing analogous queries on semantically related terms and mapping their answers back into the context of the original query using displacement vectors, we are able to give approximate answers to many questions which, if posed to the KB alone, would return no results. We also show how the hand-curated knowledge in a KB can be used to increase the accuracy of a DSVS in solving analogy problems. In these ways, a KB and a DSVS can make up for each other's weaknesses.