神经网络机器翻译的认知隐喻解构
Cognitive Metaphor-Based Analysis of Neural Machine Translation Mechanism
刘济超 1吕世生 2刘成盼3
作者信息
- 1. 同济大学 外国语学院,上海 200092
- 2. 北京语言大学 高级翻译学院,北京 100083
- 3. 中国民航大学 中欧航空工程师学院,天津 300300
- 折叠
摘要
经过基于规则、基于实例、基于统计的研究发展,神经网络机器翻译质量达到新高,在ChatGPT问世后引发了前所未有的关注.文章从认知隐喻学视角出发,结合与其同具认知功用的框架理论,探讨了人类神经网络源框架到人工神经网络目标框架的基础映射关系、深层次的蕴涵以及隐喻的连贯性;在此基础上,分别结合隐喻推理模式和隐喻的种属和类属之分探究了注意力机制和训练机制.通过挖掘其中蕴含的隐喻元素,为解构神经机器翻译提供了认知视角.
Abstract
After the development of rule-based,example-based,and statistical translation research,the advances in neural machine translation has qualitatively refined machine translation,and attracted unprecedented attention after the advent of ChatGPT.On the grounds of cognitive metaphor and integrating the framing theory which features the same cognitive function,this paper explores the fundamental mapping relations between the source frame of human neural networks and the target frame of artificial neural networks,profound connotations and metaphorical coherence.On that basis,the attention mechanism and training mechanism in neural machine translation are probed into by combining the metaphorical reasoning,and the generic level and specific-level within the scope of metaphor.By inquiring into the metaphorical elements contained in neural machine translation,this paper provides a cognitive perspective for deconstructing neural machine translation.
关键词
神经网络机器翻译/认知隐喻/框架/注意力机制/训练机制Key words
neural machine translation/cognitive metaphor/frame/attention mechanism/training mechanism引用本文复制引用
基金项目
国家社科基金学术外译项目(21WYSB019)
天津市教委科研计划项目(人文社科)(2021SK035)
出版年
2024
NETL
NSTL
万方数据