CENTRA 8 - Taiwan

This keynote provides a comprehensive overview of our work in advancing speech AI and large language models tailored for Taiwan's national languages. We chronicle our journey—from initial data collection and model training to the successful deployment of real-world applications—while examining both our methodologies and the challenges that persist. Looking ahead, the presentation highlights promising future directions for collaboration, including initiatives for endangered language revitalization, the evolution of AI-assisted language learning, and the integration of robotics to enable interactive applications. These efforts are complemented by broader cross-disciplinary partnerships, all aimed at preserving and celebrating not only Taiwan's unique linguistic heritage but also the broader spectrum of humanity's rich linguistic and cultural legacy.

The rapid development of large language models (LLMs) has introduced unprecedented possibilities in the field of humanities research. In Taiwan, the TAIwan HUmanities Conversational AI Knowledge Discovery System (TAIHUCAIS) integrates unique Taiwanese data with advanced AI technologies to address challenges related to fragmented data management and complex query requirements in humanities research. Grounded in user experience research, the system offers an intuitive conversational platform that streamlines the knowledge discovery process to meet the needs of humanities scholars. This presentation will share the development journey of TAIHUCAIS, including real-world application outcomes, and explore challenges encountered while integrating Taiwanese humanities data, such as difficulties in obtaining data authorization and issues of LLMs bias. Additionally, it will explore how these experiences can inspire research endeavors in other cultural and linguistic contexts, paving the way for future collaborations between LLMs and IT, and further promoting innovation and international connectivity.