扫码分享
中国科技术语 ›› 2025, Vol. 27 ›› Issue (3): 78-81.doi: 10.12339/j.issn.1673-8578.2025.03.012
• 科技翻译 • 上一篇 下一篇
谭洪鑫()
收稿日期:
出版日期:
发布日期:
作者简介:
谭洪鑫(2001—),女,四川外国语大学在读研究生,文学硕士,主要从事机器翻译研究。通信方式:refrain91@outlook.com。
基金资助:
TAN Hongxin()
Received:
Online:
Published:
摘要：
随着中日两国科学交流日益频繁,专利文件及其翻译需求迅速增长。在机器翻译广泛应用的背景下,探讨专利文本的机器翻译尤为重要。该研究选取Google翻译、文心一言(4.0)和ChatGPT(4.0),重点分析其在电子通信领域中的专业术语翻译情况。采用BLEU自动评估指标和多人人工评价相结合的评估方式,比较三个机器的翻译效果,归纳出误译特征并提出相应的译后编辑策略。
关键词: 专利文本, 术语翻译, 机器翻译质量评估, 译后编辑策略
Abstract:
With the increasing frequency of scientific exchanges between China and Japan,the demand for patent documents and their translation has grown rapidly.In the context of the widespread application of machine translation,it is particularly important to explore the machine translation of patent texts.This study selected Google Translate,Wenxinyiyan (4.0) and ChatGPT (4.0) to focus on analyzing their translation of professional terms in the field of electronic communications.Combining the BLEU automatic evaluation index and multi-person manual.We compared the translation effects of the three machines,summarized the mistranslation features and proposed corresponding post-editing strategies.
Key words: patent text, Terminology Translation, machine translation quality assessment, post-editing strategy
谭洪鑫. 机器翻译质量评估与译后编辑策略研究——以中日专利文本为中心[J]. 中国科技术语, 2025, 27(3): 78-81.
TAN Hongxin. Machine Translation Quality Assessment and Post-Editing Strategies:A Case Study of Chinese-Japanese Patent Texts[J]. China Terminology, 2025, 27(3): 78-81.
/ 推荐
导出引用管理器 EndNote|Ris|BibTeX
链接本文: https://www.term.org.cn/CN/10.12339/j.issn.1673-8578.2025.03.012
https://www.term.org.cn/CN/Y2025/V27/I3/78
)
