Abstract
“小句复合体由小句组合而成,不同语言在小句的组合模式上存在差异,该差异对机器翻译有何影响尚不清楚。本文以汉英机器翻译为例,选取多语体的汉语小句复合体及专家译文,从话头共享关系和共享类型两方面对主流机器翻译系统以及ChatGPT开展调查。结果显示,与专家译文相比,机器翻译的小句复合体转换生成能力存在较大不足,表现为机器翻译在话头补足、转换、提炼等方面的能力较弱,小句组合模式单一且带有明显的汉语原文痕迹,译文的地道性受到较大影响。”- Anthology ID:
- 2023.ccl-1.9
- Volume:
- Proceedings of the 22nd Chinese National Conference on Computational Linguistics
- Month:
- August
- Year:
- 2023
- Address:
- Harbin, China
- Editors:
- Maosong Sun, Bing Qin, Xipeng Qiu, Jing Jiang, Xianpei Han
- Venue:
- CCL
- SIG:
- Publisher:
- Chinese Information Processing Society of China
- Note:
- Pages:
- 102–112
- Language:
- Chinese
- URL:
- https://aclanthology.org/2023.ccl-1.9
- DOI:
- Cite (ACL):
- Fukun Xing and Jianing Xu. 2023. 面向机器翻译的汉英小句复合体转换生成能力调查(Investigation of the Clause Complexes Transfer and Generation Capability from Chinese to English for Machine Translation). In Proceedings of the 22nd Chinese National Conference on Computational Linguistics, pages 102–112, Harbin, China. Chinese Information Processing Society of China.
- Cite (Informal):
- 面向机器翻译的汉英小句复合体转换生成能力调查(Investigation of the Clause Complexes Transfer and Generation Capability from Chinese to English for Machine Translation) (Xing & Xu, CCL 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2023.ccl-1.9.pdf