用语法书提升低资源语言翻译质量
Back to School: Translation Using Grammar Books
- 将语法书作为提示词输入GPT-4，增强翻译能力
- 在16种低资源语言上验证有效，提升翻译性能
- 适合无大规模平行语料的冷门语言研究者
高资源语言的机器翻译系统表现优异，但绝大多数语言缺乏足够的平行语料进行训练。这些低资源语言虽无大量双语数据，却有可利用的双语词典和语法书等语言参考材料。借助支持近书本长度上下文的大语言模型（LLMs），我们首次探索将语法书纳入GPT-4提示词，以提升翻译性能。本文在16种拓扑差异显著的低资源语言上评估该方法，结合多种参考材料证明：通过引入语法书信息，可显著改善大模型的机器翻译效果，推动全球语言间的技术普惠。
原文摘要 · Abstract (English)
Machine translation systems for high resource languages perform exceptionally well and produce high quality translations. Unfortunately, the vast majority of languages are not considered high resource and lack the quantity of parallel sentences needed to train such systems. These under-represented languages are not without resources, however, and bilingual dictionaries and grammar books are available as linguistic reference material. With current large language models (LLMs) supporting near book-length contexts, we can begin to use the available material to ensure advancements are shared among all of the world's languages. In this paper, we demonstrate incorporating grammar books in the prompt of GPT-4 to improve machine translation and evaluate the performance on 16 topologically diverse low-resource languages, using a combination of reference material to show that the machine translation performance of LLMs can be improved using this method.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。