A Brief Survey of Multilingual Neural Machine Translation
It addresses the lack of a comprehensive survey in MNMT, which is useful for researchers and engineers interested in improving translation quality through knowledge transfer.
The paper presents a survey on multilingual neural machine translation (MNMT), categorizing existing approaches based on resource scenarios and modeling principles to help researchers and engineers navigate the field.
We present a survey on multilingual neural machine translation (MNMT), which has gained a lot of traction in the recent years. MNMT has been useful in improving translation quality as a result of knowledge transfer. MNMT is more promising and interesting than its statistical machine translation counterpart because end-to-end modeling and distributed representations open new avenues. Many approaches have been proposed in order to exploit multilingual parallel corpora for improving translation quality. However, the lack of a comprehensive survey makes it difficult to determine which approaches are promising and hence deserve further exploration. In this paper, we present an in-depth survey of existing literature on MNMT. We categorize various approaches based on the resource scenarios as well as underlying modeling principles. We hope this paper will serve as a starting point for researchers and engineers interested in MNMT.