Bandit structured prediction for neural sequence-to-sequence learning

36Citations
Citations of this article
159Readers
Mendeley users who have this article in their library.

Abstract

Bandit structured prediction describes a stochastic optimization framework where learning is performed from partial feedback. This feedback is received in the form of a task loss evaluation to a predicted output structure, without having access to gold standard structures. We advance this framework by lifting linear bandit learning to neural sequence-to-sequence learning problems using attention-based recurrent neural networks. Furthermore, we show how to incorporate control variates into our learning algorithms for variance reduction and improved generalization. We present an evaluation on a neural machine translation task that shows improvements of up to 5.89 BLEU points for domain adaptation from simulated bandit feedback.

Cite

CITATION STYLE

APA

Kreutzer, J., Sokolov, A., & Riezler, S. (2017). Bandit structured prediction for neural sequence-to-sequence learning. In ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers) (Vol. 1, pp. 1503–1513). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/P17-1138

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free