Domain-agnostic Question-Answering with Adversarial Training
By Seanie Lee, Donggyu Kim, Jangwon Park. 2019
73 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Question Answering & Reading Comprehension
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Luke S. Zettlemoyer
- Mohit Bansal
- Percy Liang
- Hannaneh Hajishirzi
- Danqi Chen
- Robin Jia
- Eunsol Choi
- Jonathan Berant
In Computer Vision and Pattern Recognition
- Robin Jia
- Danqi Chen
- Eunsol Choi
- Minjoon Seo
- Hannaneh Hajishirzi
- Alon Talmor
- Luke S. Zettlemoyer
- Percy Liang
In Question Answering & Reading Comprehension
- Eunsol Choi
- Danqi Chen
- Alon Talmor
- Robin Jia
- Jonathan Berant
- Ashish Sabharwal
- Tushar Khot
- Peter Clark
Citations in the corpus
- The Effect of Natural Distribution Shift on Question Answering Models (2020, neutral): “Bert-Large+Adv Train (Lee et al., 2019) https://worksheets.”
- MRQA 2019 Shared Task: Evaluating Generalization in Reading Comprehension (2019, background): “Train (Lee et al., 2019) The submission from 42Maru and Samsung Research proposes an adversarial training framework, where a domain discriminator predicts the underlying domain label from the QA model’s hidden representations, while the QA model tries to learn to arrange its hidden representations…”