Bandit Structured Prediction for Neural Sequence-to-Sequence Learning

Julia Kreutzer, Artem Sokolov, Stefan Riezler


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.
Anthology ID:
P17-1138
Volume:
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2017
Address:
Vancouver, Canada
Editors:
Regina Barzilay, Min-Yen Kan
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1503–1513
Language:
URL:
https://aclanthology.org/P17-1138
DOI:
10.18653/v1/P17-1138
Bibkey:
Cite (ACL):
Julia Kreutzer, Artem Sokolov, and Stefan Riezler. 2017. Bandit Structured Prediction for Neural Sequence-to-Sequence Learning. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1503–1513, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
Bandit Structured Prediction for Neural Sequence-to-Sequence Learning (Kreutzer et al., ACL 2017)
Copy Citation:
PDF:
https://aclanthology.org/P17-1138.pdf
Poster:
 P17-1138.Poster.pdf