Abstract
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.- Anthology ID:
- D19-5826
- Volume:
- Proceedings of the 2nd Workshop on Machine Reading for Question Answering
- Month:
- November
- Year:
- 2019
- Address:
- Hong Kong, China
- Venue:
- WS
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 196–202
- Language:
- URL:
- https://aclanthology.org/D19-5826
- DOI:
- 10.18653/v1/D19-5826
- Cite (ACL):
- Seanie Lee, Donggyu Kim, and Jangwon Park. 2019. Domain-agnostic Question-Answering with Adversarial Training. In Proceedings of the 2nd Workshop on Machine Reading for Question Answering, pages 196–202, Hong Kong, China. Association for Computational Linguistics.
- Cite (Informal):
- Domain-agnostic Question-Answering with Adversarial Training (Lee et al., 2019)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/D19-5826.pdf
- Code
- seanie12/mrqa
- Data
- DROP, DuoRC, RACE, SQuAD