将新加坡口语英语翻译成标准英语，助力跨语言理解与分析
What talking you?: Translating Code-Mixed Messaging Texts to English
- 用多步提示法在5个大模型上实现混语检测与翻译
- 发现大模型在混语翻译中表现不佳，存在显著挑战
- 适合对多语言沟通、社会语言学感兴趣的读者
将混杂语文本翻译为正式英语可使更广泛受众理解这些语言，并支持情感分析等下游应用。本文聚焦于新加坡口语英语（Singlish）向标准英语的翻译。Singlish由多种亚洲语言和方言混合而成。我们分析了其他亚洲语言成分对翻译的辅助作用，数据集为新加坡人之间非正式交流的短消息文本。采用五种大语言模型，通过多步提示策略进行语言识别与翻译。分析表明，大模型在此任务上表现不佳，揭示了混杂语翻译的关键难点。相关数据集已公开于 https://github.com/luoqichan/singlish。
原文摘要 · Abstract (English)
Translation of code-mixed texts to formal English allow a wider audience to understand these code-mixed languages, and facilitate downstream analysis applications such as sentiment analysis. In this work, we look at translating Singlish, which is colloquial Singaporean English, to formal standard English. Singlish is formed through the code-mixing of multiple Asian languages and dialects. We analysed the presence of other Asian languages and variants which can facilitate translation. Our dataset is short message texts, written as informal communication between Singlish speakers. We use a multi-step prompting scheme on five Large Language Models (LLMs) for language detection and translation. Our analysis show that LLMs do not perform well in this task, and we describe the challenges involved in translation of code-mixed languages. We also release our dataset in this link https://github.com/luoqichan/singlish.
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。