Using a Distributional Semantic Vector Space with a Knowledge Base for Reasoning in Uncertain Conditions

TL;DR

This paper introduces Displacer, a system combining a knowledge base with a distributional semantic vector space to improve reasoning under uncertainty by answering queries beyond the KB's explicit content.

Contribution

The paper presents a novel method integrating KBs with word2vec-based semantic vectors to enhance reasoning and analogy solving capabilities.

Findings

Enables approximate answers to queries with missing KB information.

Improves analogy problem solving using KB data to refine DSVS.

Combines KB and DSVS strengths for better reasoning under uncertainty.

Abstract

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.