计算机与现代化 ›› 2021, Vol. 0 ›› Issue (04): 27-31.

• 人工智能 • 上一篇    下一篇

基于双向GRU神经机器模型的乡土小说翻译方法

  

  1. (1.商洛学院人文学院,陕西商洛726000;2.商洛学院电子信息与电气工程学院,陕西商洛726000;
    3.西南大学外国语学院,重庆400715)
  • 出版日期:2021-04-22 发布日期:2021-04-25
  • 作者简介:孙李丽(1985—),女,山东莒南人,讲师,硕士,研究方向:语言学及应用,E-mail: sllviv1985@163.com; 郭琳(1980—),男,陕西柞水人,副教授,硕士,研究方向:人工智能与程序设计,E-mail: guolin0303@163.com; 文旭(1963—),男,四川渠县人,教授,博士生导师,博士,研究方向:认知语言学,E-mail: xuwen@swu.edu.cn。
  • 基金资助:
    商洛学院服务地方项目(18SKY-FWDF009); 国家社会科学基金重大项目(15ZDB099)

Rural Novel Translation Methods Based on Bidirectional GRU Neural Network Machine Model

  1. (1. School of Humanities, Shangluo University, Shangluo 726000, China;
    2. Electronic Information and Electrical Engineering College, Shangluo University, Shangluo 726000, China;
    3. College of International Studies, Southwest University, Chongqing 400715, China)
  • Online:2021-04-22 Published:2021-04-25

摘要: 为了提高小说作品机器翻译的准确性和效率,提出一种基于端到端的RNN神经网络框架,使用汉译英机器模型,研究乡土小说的翻译方法。通过分析RNN-NMT基础模型、WordNet语义相似度模型、GRU-LM单向门控相似度模型和BiGRU-LM双向门控相似度模型的翻译原理及优缺点,创建融合注意力机制的新模型BiGRU-LM-Attention,开展翻译测试和质量性能评价。实验表明,新模型的BLEU评价值高于其他模型;同时经过实例翻译的质量评估比较,新模型的正确率优于4种在线翻译工具,在语义识别、方言、专用名词、俚语和被动语态灵活识别方面性能突出,说明改进的神经机器模型能适应小说作品的特色语言,有效提高了翻译质量,对于传播中国文化作品具有重要意义。

关键词: 神经机器翻译, 双向GRU, 注意力机制, 《高兴》, 乡土小说

Abstract: In order to improve the accuracy and efficiency of machine translation of novels, an RNN neural network framework based on end to end is proposed to study the rural novel translation methods by using the Chinese to English machine model. By analyzing the translation principles and performance of the RNN-NMT model, WordNet Semantic Similarity model, GRU-LM model and BiGRU-LM model, the new BiGRU-LM-Attention machine model is established to carry out translation testing and quality performance evaluation. Tests prove that the BLEU value of the new model is higher than these of other models; at the same time, on the quality performance of example translation, the accuracy rate of new model is ahead of 4 online translating tools in terms of semantic recognition, dialects, special nouns, slang and flexible recognition of passive voice, indicating that the improved neural machine model in this paper can adapt to the characteristic language of the novel and effectively improve the translation quality, which is of significance of Chinese culture transmission.

Key words: neural machine translation, bidirectional GRU, attention mechanism, Happy Dreams, rural novel