论文标题
连续的机器阅读理解理解是通过不确定性感知的固定记忆和对抗域的适应
Continual Machine Reading Comprehension via Uncertainty-aware Fixed Memory and Adversarial Domain Adaptation
论文作者
论文摘要
连续的机器阅读理解旨在在不访问先前的可见数据的情况下逐步从连续的数据流中学习，这对于实际开发现实世界MRC系统至关重要。但是，在不忘记以前的知识的情况下，逐步学习一个新的领域是一个巨大的挑战。在本文中，提出了MA-MRC，这是一种持续的MRC模型，具有不确定性感知的固定记忆和对抗域的适应性。在MA-MRC中，固定尺寸内存将少数样本存储在先前的域数据中，以及新域数据到达时不确定性的更新策略。对于增量学习，MA-MRC不仅通过学习记忆和新域数据来保持稳定的理解，而且还通过对抗性学习策略充分利用它们之间的域适应关系。实验结果表明，MA-MRC优于强基础，并且具有实质性的增量学习能力，而没有灾难性地忘记在两个不同的持续MRC设置下。
Continual Machine Reading Comprehension aims to incrementally learn from a continuous data stream across time without access the previous seen data, which is crucial for the development of real-world MRC systems. However, it is a great challenge to learn a new domain incrementally without catastrophically forgetting previous knowledge. In this paper, MA-MRC, a continual MRC model with uncertainty-aware fixed Memory and Adversarial domain adaptation, is proposed. In MA-MRC, a fixed size memory stores a small number of samples in previous domain data along with an uncertainty-aware updating strategy when new domain data arrives. For incremental learning, MA-MRC not only keeps a stable understanding by learning both memory and new domain data, but also makes full use of the domain adaptation relationship between them by adversarial learning strategy. The experimental results show that MA-MRC is superior to strong baselines and has a substantial incremental learning ability without catastrophically forgetting under two different continual MRC settings.
