@InProceedings{LawrenceETAL:17a, author = {Lawrence, Carolin and Sokolov, Artem and Riezler, Stefan}, title = {Counterfactual Learning from Bandit Feedback under Deterministic Logging : A Case Study in Statistical Machine Translation}, booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing}, month = {September}, year = {2017}, address = {Copenhagen, Denmark}, publisher = {Association for Computational Linguistics}, pages = {2556--2566}, url = {https://www.aclweb.org/anthology/D17-1271} }