arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1910.09342cs.CL
收藏

具有对抗性训练的领域不可知问答

Domain-agnostic Question-Answering with Adversarial Training

Maru(42Maru);Samsung Research(三星研究院)

Seanie Lee, Donggyu Kim, Jangwon Park

摘要:

在深度学习中,在不进行微调的情况下使模型适应新的领域是一个具有挑战性的问题。在本文中,我们利用对抗训练框架的领域泛化在问答(QA)任务。我们的模型包括一个传统的QA模型和一个QA模型。训练以对抗的方式进行,两个模型不断竞争,因此QA模型可以学习域不变特征。我们在MRQA共享任务2019中应用了这种方法,并显示出比基线模型更好的性能。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑