检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:何长睿
机构地区:[1]曲阜师范大学外国语学院,山东 曲阜
出 处:《现代语言学》2024年第10期334-345,共12页Modern Linguistics
摘 要:本研究从准确性、可读性、创造性、风格和文化适应度5个维度对ChatGPT的译文进行人工评测,通过观察有无译前编辑的两组译文在5个维度的表现来评估编辑的有效性、探索编辑方法。研究发现:1) 译前编辑主要侧重于语义和文化方面,编辑后的译文在准确性、可读性方面具有显著提升。2) 译前编辑体现了人类的创意和主体性,使机器能捕捉到原文的意蕴及情感,减少了译后编辑的不确定性和所需时间。3) 由于机翻错误的不可预知性,译前编辑并不能解决译文存在的所有问题。若想获得高质量的译文,译前编辑和译后编辑在人机协作中都不可或缺。Through human evaluation of ChatGPT translation texts from five aspects: accuracy, readability, creativity, style and cultural adaptation, this study aims to explore the effectiveness and strategies of the pre-editing. The study yields the following findings: 1) Pre-editing strategies are mainly based on semantic and cultural levels, letting the translation texts have a significant improvement in accuracy and readability. 2) Pre-editing reflects the creativity and subjectivity of human, enabling the machine to capture the connotations and emotions of the original texts, and reducing the uncertainty and time required for post-editing. 3) Due to the unpredictability of machine errors, pre-editing cannot resolve all problems of translation texts. Both post-editing and pre-editing are indispensable during the human-machine cooperation process.
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.38