Measuring the behavioral impact of machine translation quality improvements with A/B testing Ben Russell author Duncan Gillespie author 2016-11 text Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing Jian Su editor Kevin Duh editor Xavier Carreras editor Association for Computational Linguistics Austin, Texas conference publication russell-gillespie-2016-measuring 10.18653/v1/D16-1251 https://aclanthology.org/D16-1251/ 2016-11 2295 2299