With the maturity of deep learning technology, reading comprehension model (given an article and a question, the AI model automatically finds the answer to the question from the article) has become a key element in natural language applications. Such as knowledge extraction and knowledge graph construction can be solved through reading comprehension model. In this project, we investigate the employment of the reading comprehension model to build an agricultural knowledge graph from Taiwan agricultural literatures. One challenge, however, is that existing reading comprehension models are not tailored for agricultural literature and therefore cannot be used directly. In this project, we leverage the question generation technology as a mechanism for agricultural data augmentation, and then train the literature reading comprehension model in the agricultural field.

The project is to establish an AUV system capable of performing underwater exploration and ecological surveys in various shallow water areas over a long period. This system can automate the collection, analysis, and recording of coral reef ecosystems' imaging, acoustic and hydrological data in designated areas.

This project collaborates with the international team to collect a very large-scale Chinese emotional corpus. In terms of technology, the fairness of speech emotion recognition is also discussed to solve social issues that may be encountered regarding the usability of emotion recognition. Among them, it is found that the database annotations are all labeled with the unfair perspective of men and women, which leads to biases in the trained model. In order to solve this problem, there have been preliminary achievements in the technological development of fairness, and will be submitted in the near future.

The NeRF-based technique describes a super-fast convergence approach to reconstructing the per-scene radiance field from a set of images that capture the scene with known poses.