Baby Bliss Bot

Blissymbolics and human-centered AI for the purpose of inclusion in

The Baby Bliss Bot project delves into the realm of using AI tools for language development and translation to enhance communication for AAC users who rely on a minority language system. This article examines the background of Blissymbolics, the potential of AI technology, and the objectives of the project.

Blissymbolics, a universal symbol language originally developed by Charles K. Bliss for the purpose of international communication, has gained popularity as a method for assisting language development and communication skills to children with physical disabilities who are non-speaking. The origin of the use of Bliss as a bridge to communication and literacy can be traced back to the pioneer program initiated by Shirley McNaughton at the Ontario Crippled Children’s Centre in 1971. Blissymbols offer a written semantic language without phonology that serves as a valuable alternative for nonvocal individuals, such as those with cerebral palsy, who face obstacles in acquiring phonological language skills.

The rapid advancement of AI technology, particularly Large Language Models (LLMs), presents not only a tremendous opportunity to enhance societal engagement for nonvocal individuals but also comes with many risks for a group that is not recognized or included in the training data. The Baby Bliss Bot (BBB) project is a community-led investigation to explore the possibilities and challenges of leveraging AI to improve communication among Bliss users, while exploring alternative ways of training and tuning AI systems to serve individuals and groups who are outliers and marginalized minorities.

The BBB project sets forth several key goals:

Investigating visual language systems and generative language models.
Exploring the process of co-learning with machine learning models.
Preserving the plasticity of formalized language or maintaining a living language while safeguarding its essence.

The insights shared by AAC users underscore several crucial aspects:

Enabling Blissymbolics to serve as a semantic shorthand, expanding meaning effectively for unfamiliar listeners in a context-specific and adaptive manner.
Personalizing vocabulary, presentation, and input to meet the unique needs of each AAC user.
Assisting with the transition to literacy, particularly for second language learners.

The Baby Bliss Bot project anticipates yielding valuable insights and specifications for the development of adaptive AI-based AAC systems. Alongside these findings, the project aims to create experimental prototypes, pushing the boundaries of communication accessibility for AAC users.

By delving into the intersection of AI tools, language learning, and communication enhancement for AAC users, the Baby Bliss Bot project aspires to empower individuals utilizing Blissymbolics. Through collaborative exploration and innovation, the project strives to foster inclusivity and break barriers, ultimately improving the lives of nonvocal individuals within minority language systems.

Academic outputs

Articles

Presentations

Final ISAAC Presentation

The rapid advancement of AI - particularly Large Language Models (LLMs) - offers exciting possibilities to enhance communication for AAC users. The inclusive design project described in this paper, titled Baby Bliss Bot, is led by a group of AI programmers collaborating with AAC users as co-designers in an interdisciplinary initiative. It uses Blissymbolics in its first phase to explore how the LLMs of AI can be leveraged to support AAC users in learning language and in communicating meaningfully across contexts and dialogue types - at home, in school, at work and from inquiry and discovery, to humour, creativity and beyond. Blissymbolics was chosen as the GRS in Phase One because of its comprehensive language capabilities and affordances that facilitated a multi-tiered approach. Through collaborative experimentation, the project investigates not only how to make AI systems more inclusive for outliers and minorities, but also how to design alternative training methods and interfaces. The aim is to support context-aware, personalized expression that respects the individuality of each AAC user.

https://www.youtube.com/watch?v=lLgNm_g5slc