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.

该论文提出了 MA-MRC，一种使用具有不确定性意识的固定内存和对抗领域适应的连续 MRC 模型，旨在在不访问以前见过的数据的情况下，从连续数据流中学习。实验结果表明，MA-MRC 具有显着的增量学习能力，没有灾难性遗忘在两个不同的连续 MRC 设置下。