Continual Learning for Temporal-Sensitive Question Answering

TL;DR

This paper investigates continual learning strategies for temporal-sensitive question answering, emphasizing model adaptation over time, and introduces a new dataset and training framework to address the unique challenges of evolving information.

Contribution

It presents a novel dataset for CLTSQA and proposes a training framework combining temporal memory replay and contrastive learning, advancing the field of continual temporal question answering.

Findings

The CLTSQA task poses unique challenges for existing models.

The proposed framework improves performance in continual temporal question answering.

Experimental results validate the effectiveness of the framework.

Abstract

In this study, we explore an emerging research area of Continual Learning for Temporal Sensitive Question Answering (CLTSQA). Previous research has primarily focused on Temporal Sensitive Question Answering (TSQA), often overlooking the unpredictable nature of future events. In real-world applications, it's crucial for models to continually acquire knowledge over time, rather than relying on a static, complete dataset. Our paper investigates strategies that enable models to adapt to the ever-evolving information landscape, thereby addressing the challenges inherent in CLTSQA. To support our research, we first create a novel dataset, divided into five subsets, designed specifically for various stages of continual learning. We then propose a training framework for CLTSQA that integrates temporal memory replay and temporal contrastive learning. Our experimental results highlight two significant insights: First, the CLTSQA task introduces unique challenges for existing models. Second, our proposed framework effectively navigates these challenges, resulting in improved performance.