arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.12470cs.CL
收藏

面向时间敏感问答的持续学习

Continual Learning for Temporal-Sensitive Question Answering

University of Technology Sydney(悉尼科技大学);University of Sydney(悉尼大学);Hangzhou Dianzi University(杭州电子科技大学)

Wanqi Yang, Yunqiu Xu, Yanda Li, Kunze Wang, Binbin Huang, Ling Chen

AI总结:

本研究针对时间敏感问答的持续学习问题,构建了五子集数据集,并提出融合时间记忆回放与时间对比学习的训练框架,有效应对动态信息环境下的挑战,提升模型性能。

摘要:

在本研究中,我们探索了持续学习用于时间敏感问答(CLTSQA)这一新兴研究领域。以往的研究主要聚焦于时间敏感问答(TSQA),常常忽视未来事件的不可预测性。在现实应用中,模型持续获取随时间变化的知识至关重要,而非依赖于静态、完整的数据集。我们的论文研究了使模型能够适应不断演变的信息格局的策略,从而应对CLTSQA中固有的挑战。为支持我们的研究,我们首先创建了一个新颖的数据集,将其划分为五个子集,专门设计用于持续学习的各个阶段。随后,我们提出了一种用于CLTSQA的训练框架,该框架整合了时间记忆回放和时间对比学习。我们的实验结果凸显了两个重要见解:第一,CLTSQA任务为现有模型带来了独特挑战;第二,我们提出的框架有效应对了这些挑战,从而提升了性能。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑