基于中间语言级联翻译模型的端到端训练与解码（英文版）

英文标题：End-to-end Training and Decoding for Pivot-based Cascaded Translation Model中文摘要：本文提出了一种基于端到端训练方法的级联翻译模型，并配置了一种改进的解码算法，该方法可以有效地利用极少量的 (parallel) data 来提高翻译质量。英文摘要：Utilizing pivot language effectively can significantly improve low-resourcemachine translation. Usually, the two translation models, source-pivot andpivot-target, are trained individually and do not utilize the limited (source,target) parallel data. This work proposes an end-to-end training method for thecascaded translation model