Chatgpt-4 C-Lara-Instance


2024

pdf
T is for Treu, but how do you pronounce that? Using C-LARA to create phonetic texts for Kanak languages
Pauline Welby | Fabrice Wacalie | Manny Rayner | Chatgpt-4 C-Lara-Instance
Proceedings of the Seventh Workshop on the Use of Computational Methods in the Study of Endangered Languages

In Drehu, a language of the indigenous Kanak people of New Caledonia, the word treu ‘moon’ is pronounced [{tSe.u}]; but, even if they hear the word, the spelling pulls French speakers to a spurious pronunciation [tK{o}]. We implement a strategy to mitigate the influence of such orthographic conflicts, while retaining the benefits of written input on vocabulary learning. We present text in “phonetized” form, where words are broken down into components associated with mnemonically presented phonetic values, adapting features from the “Comment ça se prononce~?” multilingual phonetizer. We present an exploratory project where we used the ChatGPT-based Learning And Reading Assistant (C-LARA) to implement a version of the phonetizer strategy, outlining how the AI-engineered codebase and help from the AI made it easy to add the necessary extensions. We describe two proof-of-concept texts for learners produced using the platform, a Drehu alphabet book and a Drehu version of “The (North) Wind and the Sun”; both texts include native-speaker recorded audio, pronunciation respellings based on French orthography, and AI-generated illustrations.