Recognizing Temporal Relations in Natural Language based on CCG and Theorem Proving

Abstract

Recognizing temporal relations among events and time expressions has been one of the most challenging tasksin natural language processing. Recent studies mainly focus on deep learning-based models trained with a largetemporal relation corpus. However, it is unclear whether these models can accurately perform complex inferenceswith temporal phenomena. In this paper, we present an inference system to perform inferences over temporalrelations. We use a higher-order inference system based on Combinatory Categorial Grammar (CCG), a systemthat converts input sentences to semantic representations via derivation trees and proves entailment relations viatheorem proving. We show that by adding lexical entries and axioms for temporal relations, the system can performlogical inferences over multiple temporal relations.