摘要
为提高机器翻译的质量和效率,研究利用遗传算法(Genetic Algorithm,GA)和粒子群算法(Particle Swarm Optimization,PSO)对前馈神经网络(Back Propagation,BP)算法进行了改进,基于改进算法构建了自动化翻译及矫正模型。实验结果表明,该模型的翻译精确率为97.23%,召回率为94.00%,准确率为97.5%,F1值为94.00%,翻译平均耗时1分钟。该模型对语句的错译问题明显改善,可见翻译的精度较高且随着翻译量的增加不会明显降低,翻译的效率也较高,可以满足实际的翻译需求。同时该模型有利于提高机器翻译的质量和效率,帮助矫正机器翻译的错译问题,纠正英汉机器翻译的错误,可以为人们提供性能更强的机器翻译工具,满足自动化英译汉翻译和错译矫正需求。
In order to improve the quality and efficiency of machine translation,genetic algorithm(GA) and particle swarm optimization(PSO) were used to improve the Back Propagation(BP) algorithm of feedforward neural networks.Based on the improved algorithm,an automated translation and correction model was constructed.The experimental results show that the translation accuracy of the model is 97.23%,the recall rate is 94.00%,the accuracy rate is 97.5%,the F1 value is 94.00%,and the average translation time is 1 minute.This model significantly improves the issue of mistranslation of sentences,indicating that the accuracy of translation is high and will not significantly decrease with the increase of translation volume.The efficiency of translation is also high,which can meet practical translation needs.At the same time,this model is conducive to improving the quality and efficiency of machine translation,helping to correct mistranslation problems in machine translation,and correcting errors in English Chinese machine translation.It can provide people with stronger machine translation tools to meet the needs of automated English Chinese translation and mistranslation correction.
作者
李潇
LI Xiao(Xianyang Normal University,Xianyang Shaanxi 712000,China)
出处
《自动化与仪器仪表》
2023年第11期20-24,共5页
Automation & Instrumentation
基金
咸阳师范学院校级科研项目《大数据时代背景下互联网翻译模式与运行机制研究》(XSYK22005)。
关键词
人工神经网络
机器翻译
自动矫正
BP
GA
PSO
artificial neural network
machine translation
automatic correction
BP
GA
PSO
