What talking you?: Translating Code-Mixed Messaging Texts to English
This addresses the problem of making informal, multilingual communication accessible for analysis, but it is incremental as it focuses on a specific dataset and reveals limitations without major breakthroughs.
The paper tackled translating code-mixed Singlish messages to formal English, finding that large language models perform poorly on this task and highlighting the challenges involved.
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.