A Weakly Supervised Approach to Train Temporal Relation Classifiers and Acquire Regular Event Pairs Simultaneously
This addresses the need for temporal relation detection in applications like natural language processing, offering a method to reduce annotation costs while maintaining accuracy, though it is incremental in leveraging weak supervision.
The paper tackled the problem of detecting temporal relations between events by proposing a weakly supervised approach that simultaneously extracts regular event pairs and trains a contextual classifier, achieving comparable performance to state-of-the-art supervised systems.
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.