是否LLM翻译与翻译通用性保持一致? 一项基于依赖语法英语中文翻译的跨类型简化研究
1School of Foreign Languages, Qingdao University, Qingdao, Shandong, China.
PloS one
|June 2, 2025
概括
语法简化,一种通用的翻译,在人类和大型语言模型 (LLM) 从英语到中文的翻译中都被发现. 人类翻译显示出比LLM翻译更强的简化趋势.
科学领域:
- 计算语言学 计算语言学
- 翻译研究 翻译研究
- 自然语言处理自然语言处理.
背景情况:
- 翻译通用 (TU) 是翻译文本的共同特征.
- 简化是一个提议的TU,表明翻译往往比原始更不复杂.
- 语法复杂性可以用平均依赖距离 (MDD) 和平均等级距离 (MHD) 来衡量.
研究的目的:
- 调查英语到中文翻译中的语法简化.
- 为了比较人类和大型语言模型 (LLM) 翻译之间的简化水平.
- 评估MDD和MHD作为翻译研究中语法复杂性的指标.
主要方法:
- 分析了三个平衡的可比的英语翻译和原始中文文本.
- 平均依赖距离 (MDD) 和平均等级距离 (MHD) 在15个类型中的比较.
- 统计分析以确定语法复杂性的显著差异.
主要成果:
- 与所有类型的原始中文文本相比,人类翻译和LLM翻译都表现出显著的语法简化.
- 人类翻译显示出比LLM翻译更明显的简化趋势.
- MDD和MHD证明了对语法复杂性的有效整体措施.
结论:
- 这项研究验证了英语到中文翻译的语法层面上的简化假设.
- 简化的差异突出了人类与LLM翻译中的独特的认知和处理机制.
- 研究结果为LLM开发和LLM辅助翻译策略提供了洞察力.
相关概念视频
Language and Cognition
466
Language serves as a bridge between ideas and communication, influencing how individuals perceive and interact with the world. Psychologists have long debated whether language shapes thought or vice versa. This discussion gained grip with Edward Sapir and Benjamin Lee Whorf in the 1940s, who proposed that language determines thought, a concept known as linguistic determinism. They suggested that the vocabulary and structure of a language influence how its speakers think and perceive reality.
466
Components of Language
416
Language, whether spoken, signed, or written, consists of specific components: lexicon and grammar. The lexicon is the vocabulary of a language, comprising its words. Grammar is the set of rules used to convey meaning through the lexicon. For example, English grammar adds “-ed” to most verbs to indicate past tense. Words are formed by combining phonemes, which are the basic sound units of a language. Different languages have different sets of phonemes (e.g., “ah” vs.
416
Termination of Translation
5.6K
5.6K
Improving Translational Accuracy
2.7K
2.7K
Leaky Scanning
5.2K
During most eukaryotic translation processes, the small 40S ribosome subunit scans an mRNA from its 5' end until it encounters the first start AUG codon. The large 60S ribosomal subunit then joins the smaller one to initiate protein synthesis. The location of the translation initiation is largely determined by the nucleotides near the start codon as there may be multiple translation initiation sites present on the mRNA. Marilyn Kozak discovered that the sequence RCCAUGG (where R...
5.2K
Language Development
462
Children master language quickly and with relative ease, supported by both biological predisposition and reinforcement. B. F. Skinner (1957) proposed that language is learned through reinforcement, while Noam Chomsky (1965) argued that language acquisition mechanisms are biologically determined.
The critical period for language acquisition suggests that the ability to acquire language is at its peak early in life. As people age, this proficiency decreases. Language development begins very...
The critical period for language acquisition suggests that the ability to acquire language is at its peak early in life. As people age, this proficiency decreases. Language development begins very...
462


