计算机科学与探索2024，Vol.18Issue(7)：1725-1747,23.DOI:10.3778/j.issn.1673-9418.2311027
基于知识蒸馏的神经机器翻译综述
Survey of Neural Machine Translation Based on Knowledge Distillation
摘要
Abstract
Machine translation(MT)is the process of using a computer to convert one language into another lan-guage with the same semantics.With the introduction of neural network,neural machine translation(NMT),as a powerful machine translation technology,has achieved remarkable success in the field of automatic translation and artificial intelligence.Due to the problem of redundant parameters and structure in traditional neural translation models,knowledge distillation(KD)technology is proposed to compress the model and accelerate the inference of neural machine translation,which has attracted wide attention in the field of machine learning and natural language pro-cessing.This paper systematically investigates and compares various translation models with introduction of know-ledge distillation from the perspectives of evaluation indicators and technical innovations.Firstly,this paper briefly reviews the development process,mainstream frameworks and evaluation indicators of machine translation.Secondly,the knowledge distillation technology is introduced in detail.Thirdly,the development direction of neural machine translation based on knowledge distillation is detailed from four perspectives:multi-language model,multi-modal translation,low-resource language,autoregressive and non-autoregressive,and the research status of other fields is briefly introduced.Finally,the problems of existing large language models,zero-resource languages and multi-modal machine translation are analyzed,and the development trend of neural machine translation is prospected.关键词
机器翻译/神经机器翻译/知识蒸馏/模型压缩Key words
machine translation/neural machine translation/knowledge distillation/model compression分类
信息技术与安全科学引用本文复制引用
马畅,田永红,郑晓莉,孙康康..基于知识蒸馏的神经机器翻译综述[J].计算机科学与探索,2024,18(7):1725-1747,23.基金项目
内蒙古自治区自然科学基金(2020MS06026).This work was supported by the Natural Science Foundation of Inner Mongolia Autonomous Region(2020MS06026). （2020MS06026）
