The UMD Neural Machine Translation Systems at WMT17 Bandit Learning Task
We describe the University of Maryland machine translation systems submitted to the WMT17 German-English Bandit Learning Task. The task is to adapt a translation system to a new domain, using only bandit feedback: the system receives a German sentence to translate, produces an English sentence, and only gets a scalar score as feedback. Targeting these two challenges (adaptation and bandit learning), we built a standard neural machine translation system and extended it in two ways: (1) robust reinforcement learning techniques to learn effectively from the bandit feedback, and (2) domain adaptation using data selection from a large corpus of parallel data.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain AdaptationMachine Translationreinforcement-learningReinforcement LearningReinforcement Learning (RL)SentenceTranslationSimilar Papers 제목 키워드 기반
Machine Translation System Selection from Bandit Feedback
Adapting machine translation systems in the real world is a difficult problem. In contrast to offline training, users cannot provide the type of fine-grained feedback (such as correct translations) typically used for imp…
Machine TranslationTranslationIntroducing Mouse Actions into Interactive-Predictive Neural Machine Translation
The quality of the translations generated by Machine Translation (MT) systems has highly improved through the years and but we are still far away to obtain fully automatic high-quality translations. To generate them and …
Machine TranslationTranslationBandits Don't Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Bandits
Training data for machine translation (MT) is often sourced from a multitude of large corpora that are multi-faceted in nature, e.g. containing contents from multiple domains or different levels of quality or complexity.…
Machine TranslationMulti-Armed BanditsTranslationBandits Don’t Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Bandits
Training data for machine translation (MT) is often sourced from a multitude of large corpora that are multi-faceted in nature, e.g. containing contents from multiple domains or different levels of quality or complexity.…
Machine TranslationMulti-Armed BanditsTranslationA Shared Task on Bandit Learning for Machine Translation
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 M…
Machine TranslationTranslation