Context-Dependent Semantic Parsing for Temporal Relation Extraction

TL;DR

This paper introduces SMARTER, a neural semantic parser that effectively extracts temporal relations from text by generating logical forms, improving expressivity and consistency over previous methods.

Contribution

It proposes a novel neural semantic parsing approach with a custom typed lambda calculus and dynamic programming on denotations for weak supervision.

Findings

Achieves precise logical forms capturing temporal information

Ensures consistency among predicted temporal relations

Outperforms previous methods in temporal relation extraction

Abstract

Extracting temporal relations among events from unstructured text has extensive applications, such as temporal reasoning and question answering. While it is difficult, recent development of Neural-symbolic methods has shown promising results on solving similar tasks. Current temporal relation extraction methods usually suffer from limited expressivity and inconsistent relation inference. For example, in TimeML annotations, the concept of intersection is absent. Additionally, current methods do not guarantee the consistency among the predicted annotations. In this work, we propose SMARTER, a neural semantic parser, to extract temporal information in text effectively. SMARTER parses natural language to an executable logical form representation, based on a custom typed lambda calculus. In the training phase, dynamic programming on denotations (DPD) technique is used to provide weak supervision on logical forms. In the inference phase, SMARTER generates a temporal relation graph by executing the logical form. As a result, our neural semantic parser produces logical forms capturing the temporal information of text precisely. The accurate logical form representations of an event given the context ensure the correctness of the extracted relations.