Proceedings

Adversarial Sequence Tagging

Jia Li, Kaiser Asif, Hong Wang, Brian D. Ziebart, Tanya Y. Berger-Wolf

Download BibTeX Cite

Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence. Pages 1690-1695.

Abstract

Providing sequence tagging that minimize Hamming loss is a challenging, but important, task. Directly minimizing this loss over a training sample is generally an NP-hard problem. Instead, existing sequence tagging methods minimize a convex upper bound that upper bounds the Hamming loss. Unfortunately, this often either leads to inconsistent predictors (e.g., max-margin methods) or predictions that are mismatched on the Hamming loss (e.g., conditional random fields). We present adversarial sequence tagging, a consistent structured prediction framework for minimizing Hamming loss by pessimistically viewing uncertainty. Our approach pessimistically approximates the training data, yielding an adversarial game between the sequence tag predictor and the sequence labeler. We demonstrate the benefits of the approach on activity recognition and information extraction/segmentation tasks.

Jia Li, Kaiser Asif, Hong Wang, Brian D. Ziebart, and Tanya Y. Berger-Wolf. 2016. Adversarial Sequence Tagging. In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-16. IJCAI, 1690–1695. https://ijcai.org/proceedings/2016/242
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards