A Shared Task on Bandit Learning for Machine Translation
This addresses the problem of improving machine translation efficiency by using weak feedback, but it is incremental as it builds on existing bandit learning and translation methods.
The paper introduced a shared task on bandit learning for machine translation at WMT 2017, aiming to encourage research on learning from weak user feedback instead of human references, and described the setup and results of various machine translation architectures and learning protocols.
We introduce and describe the results of a novel shared task on bandit learning for machine translation. The task was organized jointly by Amazon and Heidelberg University for the first time at the Second Conference on Machine Translation (WMT 2017). The goal of the task is to encourage research on learning machine translation from weak user feedback instead of human references or post-edits. On each of a sequence of rounds, a machine translation system is required to propose a translation for an input, and receives a real-valued estimate of the quality of the proposed translation for learning. This paper describes the shared task's learning and evaluation setup, using services hosted on Amazon Web Services (AWS), the data and evaluation metrics, and the results of various machine translation architectures and learning protocols.