End-to-end Training and Decoding for Pivot-based Cascaded Translation Model

2023/05/03 by Hao Cheng, Cheng, Hao, Meng Zhang +6
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning and Data Classification #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2305.02261

openalex publication_date 2023/05/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Related

• Neural Machine Translation with Pivot Languages
• A Single Model Ensemble Framework for Neural Machine Translation using Pivot Translation
• Pivot-based Transfer Learning for Neural Machine Translation between Non-English Languages
• Triangular Transfer: Freezing the Pivot for Triangular Machine\n Translation
• From Words to Sentences: A Progressive Learning Approach for Zero-resource Machine Translation with Visual Pivots