A Weakly Supervised Approach to Train Temporal Relation Classifiers and Acquire Regular Event Pairs Simultaneously

TL;DR

This paper proposes a weakly supervised method to train temporal relation classifiers and acquire regular event pairs simultaneously, leveraging the consistency of event pairs across contexts to improve temporal understanding.

Contribution

It introduces a novel weakly supervised approach that extracts regular event pairs and trains a temporal relation classifier without extensive labeled data.

Findings

High-quality regular event pairs with rich knowledge are acquired.

The weakly supervised classifier performs comparably to supervised systems.

The approach effectively captures commonsense and domain-specific knowledge.

Abstract

Capabilities of detecting temporal relations between two events can benefit many applications. Most of existing temporal relation classifiers were trained in a supervised manner. Instead, we explore the observation that regular event pairs show a consistent temporal relation despite of their various contexts, and these rich contexts can be used to train a contextual temporal relation classifier, which can further recognize new temporal relation contexts and identify new regular event pairs. We focus on detecting after and before temporal relations and design a weakly supervised learning approach that extracts thousands of regular event pairs and learns a contextual temporal relation classifier simultaneously. Evaluation shows that the acquired regular event pairs are of high quality and contain rich commonsense knowledge and domain specific knowledge. In addition, the weakly supervised trained temporal relation classifier achieves comparable performance with the state-of-the-art supervised systems.