Project website

Kon ta bAI is a techno-cultural project focused on generating natural language in the Papiamentu language using Artificial Intelligence.

The central question of this project is as follows: To what extent is it possible to generate natural language in Papiamentu using AI, and how can we present this in the form of a physical installation for the public to experience?

“Kon ta bAI” translates to “how are you” in Papiamentu, a Creole language spoken by approximately 350,000 people, primarily on the islands of Aruba, Curaçao, and Bonaire (where it is one of the official languages) and in the Netherlands. We intentionally spelled “bAI” in “Kon ta bAI” with a capital A and I to highlight the first letters of “Artificial Intelligence.”

Kon ta bAI is a Natural Language Processing (NLP) system, which is a branch of AI concerned with the ability of computers to understand text and spoken language in a manner similar to humans. Currently, there are no accurate NLP systems for Papiamentu. The language is referred to as a “low-resource language” because there are not enough datasets available for training purposes for these systems. Creating datasets is often very labor-intensive and costly. In this project, we are exploring the extent to which it is possible to create an accurate NLP system for Papiamentu. We will develop software that is capable of downloading online texts. As we collect texts from public sources, newspapers, publishers, schools, and word artists, we will train an AI to generate new, grammatically correct sentences of any length in Papiamentu. We will then continue to develop the AI until it is able to produce poetic texts. Finally, we will create an art installation with the help of local visual artists to present the AI to the public.

My primary motivation for creating a Papiamentu language model comes from my interest in creating something new and technical. I am also highly interested in combining AI with art and have already completed two successful projects involving language models, The Spirit Machine and Quantum Cat. While there are already large English language models that can perform this type of work, there is currently no similar model for the Papiamentu language. As an AI researcher and a native of Curaçao, it has been my ambition for several years to create the world’s first AI Papiamentu language model. I am convinced that such a model will not only help speakers of the Papiamentu language, but also represent a significant step forward in the field of AI language modeling. In addition, a Papiamentu language model would be a valuable resource for researchers, teachers, and anyone interested in the language and culture of Papiamentu-speaking communities.