HW-TSC's Submission to the CCMT 2024 Machine Translation Tasks

TL;DR

This paper details HW-TSC's submission to CCMT 2024, employing advanced training strategies and LLM fine-tuning to enhance neural machine translation performance across multiple tasks.

Contribution

The paper introduces a comprehensive set of training techniques and the use of LLM fine-tuning to improve NMT systems for CCMT 2024.

Findings

Achieved competitive results in final evaluation.

Demonstrated effectiveness of diverse training strategies.

Showcased benefits of LLM fine-tuning for translation quality.

Abstract

This paper presents the submission of Huawei Translation Services Center (HW-TSC) to machine translation tasks of the 20th China Conference on Machine Translation (CCMT 2024). We participate in the bilingual machine translation task and multi-domain machine translation task. For these two translation tasks, we use training strategies such as regularized dropout, bidirectional training, data diversification, forward translation, back translation, alternated training, curriculum learning, and transductive ensemble learning to train neural machine translation (NMT) models based on the deep Transformer-big architecture. Furthermore, to explore whether large language model (LLM) can help improve the translation quality of NMT systems, we use supervised fine-tuning to train llama2-13b as an Automatic post-editing (APE) model to improve the translation results of the NMT model on the multi-domain machine translation task. By using these plyometric strategies, our submission achieves a competitive result in the final evaluation.