Abstract
Two types of data shift common in practice are 1. transferring from synthetic data to live user data (a deployment shift), and 2. transferring from stale data to current data (a temporal shift). Both cause a distribution mismatch between training and evaluation, leading to a model that overfits the flawed training data and performs poorly on the test data. We propose a solution to this mismatch problem by framing it as domain adaptation, treating the flawed training dataset as a source domain and the evaluation dataset as a target domain. To this end, we use and build on several recent advances in neural domain adaptation such as adversarial training (Ganinet al., 2016) and domain separation network (Bousmalis et al., 2016), proposing a new effective adversarial training scheme. In both supervised and unsupervised adaptation scenarios, our approach yields clear improvement over strong baselines.- Anthology ID:
- P17-1119
- Volume:
- Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2017
- Address:
- Vancouver, Canada
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1297–1307
- Language:
- URL:
- https://aclanthology.org/P17-1119
- DOI:
- 10.18653/v1/P17-1119
- Cite (ACL):
- Young-Bum Kim, Karl Stratos, and Dongchan Kim. 2017. Adversarial Adaptation of Synthetic or Stale Data. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1297–1307, Vancouver, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Adversarial Adaptation of Synthetic or Stale Data (Kim et al., ACL 2017)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/P17-1119.pdf