Towards Building a Logical Inference System for Text and Visual Information

Abstract

A large amount of research about multimodal inference across natural language and vision has been recently developed to obtain visually grounded word and sentence representations. In this paper, we use logic-based representations as unified meaning representations for texts and images and present an unsupervised inference system that can effectively prove entailment relations between them. We show that by combining semantic parsing and theorem proving, the system can handle semantically complex queries for image retrieval.