用词典增强提示，让ChatGPT帮濒危乌拉尔语消歧，准确率超40%。
DAG: Dictionary-Augmented Generation for Disambiguation of Sentences in Endangered Uralic Languages using ChatGPT
- 用芬兰语词典翻译候选词，增强ChatGPT提示信息
- Skolt Sami准确率达50%，Erzya达41%
- 错误类型与普通人类标注者相似，说明方法合理
我们展示，即使在非熟练领域，ChatGPT也能对两种濒危语言——埃里亚语和斯科特萨米语的词素进行消歧。通过在提示中加入候选词到主流语言（本研究中为芬兰语）的词典翻译，采用词典增强生成的方法，使斯科特萨米语的准确率达到50%，埃里亚语达到41%。深入分析发现，多数错误类型甚至普通未经训练的人类标注者也会犯，表明该方法具有实际可行性。
原文摘要 · Abstract (English)
We showcase that ChatGPT can be used to disambiguate lemmas in two endangered languages ChatGPT is not proficient in, namely Erzya and Skolt Sami. We augment our prompt by providing dictionary translations of the candidate lemmas to a majority language - Finnish in our case. This dictionary augmented generation approach results in 50\% accuracy for Skolt Sami and 41\% accuracy for Erzya. On a closer inspection, many of the error types were of the kind even an untrained human annotator would make.
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。