End-to-end Training and Decoding for Pivot-based Cascaded Translation Model
Cheng, Hao, Zhang, Meng, Li, Liangyou, Liu, Qun, Zhang, Zhihua
–arXiv.org Artificial Intelligence
Utilizing pivot language effectively can significantly improve low-resource machine translation. Usually, the two translation models, source-pivot and pivot-target, are trained individually and do not utilize the limited (source, target) parallel data. This work proposes an end-to-end training method for the cascaded translation model and configures an improved decoding algorithm. The input of the pivot-target model is modified to weighted pivot embedding based on the probability distribution output by the source-pivot model. This allows the model to be trained end-to-end. In addition, we mitigate the inconsistency between tokens and probability distributions while using beam search in pivot decoding. Experiments demonstrate that our method enhances the quality of translation.
arXiv.org Artificial Intelligence
May-3-2023
- Country:
- Oceania > Australia
- North America
- United States
- New York > Monroe County
- Rochester (0.04)
- Minnesota > Hennepin County
- Minneapolis (0.14)
- California
- San Diego County > San Diego (0.05)
- Los Angeles County > Long Beach (0.04)
- New York > Monroe County
- Canada
- Quebec > Montreal (0.04)
- British Columbia > Metro Vancouver Regional District
- Vancouver (0.04)
- United States
- Europe
- Germany > Berlin (0.04)
- Ireland > Leinster
- County Dublin > Dublin (0.04)
- Belgium > Brussels-Capital Region
- Brussels (0.04)
- Asia > China
- Hong Kong (0.04)
- Genre:
- Research Report (0.40)
- Technology: