Forget Me Not: Reducing Catastrophic Forgetting for Domain Adaptation in Reading Comprehension

The creation of large-scale open domain reading comprehension data sets in recent years has enabled the development of end-to-end neural comprehension models with promising results. To use these models for domains with limited training data, one of the most effective approach is to first pre-train them on large out-of-domain source data and then fine-tune them with the limited target data. The caveat of this is that after fine-tuning the comprehension models tend to perform poorly in the source domain, a phenomenon known as catastrophic forgetting. In this paper, we explore methods that reduce catastrophic forgetting during fine-tuning without assuming access to data from the source domain. We introduce new auxiliary penalty terms and observe the best performance when a combination of auxiliary penalty terms is used to regularise the fine-tuning process for adapting comprehension models. To test our methods, we develop and release 6 narrow domain data sets that can potentially be used as reading comprehension benchmarks.