Domain-agnostic Question-Answering with Adversarial Training
This addresses domain generalization for question-answering systems, but it appears incremental as it applies an existing adversarial approach to a specific task.
The paper tackles the problem of adapting question-answering models to new domains without fine-tuning by using an adversarial training framework, resulting in improved performance on the MRQA Shared Task 2019 compared to a baseline.
Adapting models to new domain without finetuning is a challenging problem in deep learning. In this paper, we utilize an adversarial training framework for domain generalization in Question Answering (QA) task. Our model consists of a conventional QA model and a discriminator. The training is performed in the adversarial manner, where the two models constantly compete, so that QA model can learn domain-invariant features. We apply this approach in MRQA Shared Task 2019 and show better performance compared to the baseline model.