Jangwon Park


2019

pdf bib
Domain-agnostic Question-Answering with Adversarial Training
Seanie Lee | Donggyu Kim | Jangwon Park
Proceedings of the 2nd Workshop on Machine Reading for Question Answering

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.
Search
Co-authors
Venues