About TAIHU
Taiwan possesses a wealth of rich and unique humanities data.
However, these resources are scattered across various institutions, often requiring users to spend significant time accessing multiple databases for information retrieval.
With the development of large generative conversational language models, we aim to integrate Taiwan's existing primary humanities databases with a self-developed language model to create a conversational knowledge exploration system designed specifically for humanities scholars in Taiwan.
01
Alignment with Taiwan's Context
Unlike other language models, our model is specifically designed using Taiwan-based language data, enabling it to provide dialogue responses that are highly relevant to Taiwan’s local context and culture. This ensures more precise and contextually appropriate information retrieval.
02
Enhancing Research Efficiency
With this project’s conversational knowledge exploration system, scholars can ask questions in natural language and quickly obtain integrated information from multiple databases. This significantly reduces the time needed for data retrieval, allowing researchers to focus more on their studies and improving overall research efficiency.
03
Increasing Database Usage
By simplifying the user experience and optimizing the usage process, we anticipate increased utilization of Taiwan's humanities databases and hope to attract more interest in Taiwan’s humanities research.