HW-TSC’s Neural Machine Translation System for CCMT 2023

Communications in computer and information science(2023)

Cited 0|Views0
No score
Abstract
This paper presents Huawei Translation Service Center (HW-TSC)’s submission to the machine translation tasks of the 19th China Conference on Machine Translation (CCMT 2023). We participate in all machine translation tasks, including five bilingual machine translation tasks, the Belt and Road low-resource language machine translation task, Chinese-centric multilingual machine translation task and Chinese $$\rightarrow $$ English zero-referencing machine translation task. Under different machine translation tasks, we adopt different methods to train the corresponding neural machine translation system. This paper mainly explains the model structure, data size and training method adopted by the translation systems, and gives the comparison of the evaluation results under different training methods.
More
Translated text
Key words
neural machine translation system,ccmt,hw-tsc
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined