基于大语言模型与知识增强框架的文本翻译模型研究OA

[Purpose/significance]This paper aims to improve the translation quality of large language models and effectively alleviate the translation illusion problem,thereby enhancing cross-linguistic information retrieval capabilities.[Method/process]A translation genera-tion method based on a knowledge enhancement framework is proposed.This framework optimizes the translation process from multiple dimensions,such as style,focus,and cultural adaptability,by combining external knowledge provided by the translation context building module and the knowledge base building and retrieval module,and then utilizing the guidance of the text attention module.[Result/con-clusion]Experimental results show that the proposed method effectively enhances model performance.Specifically,on the WikiLingua,TED,and CCMatrix datasets,the model's BLEU scores improved by 5.29%,5.94%,and 8.58%,respectively.In addition to traditional translation evaluation metrics,this paper also introduces a six-dimensional evaluation system based on large models and an evaluation experiment to address the translation illusion problem.Experimental results show that after applying the proposed framework to the large model,all metrics surpass those of existing mainstream translation tools.This research provides a new solution for text translation,which has significant practical implications for quickly and accurately understanding information from large amounts of foreign language data,and is helpful for intelligence gathering,analysis,and decision-making.