Refined Schema
Refined schema research focuses on improving the efficiency and accuracy of information extraction and processing from complex data sources, particularly in natural language processing and database interactions. Current efforts center on developing novel methods for schema linking, leveraging large language models (LLMs) to understand and utilize schema information more effectively, and employing techniques like prompt engineering and schema augmentation to enhance performance. This work is significant for advancing the capabilities of LLMs in handling complex data structures and improving the usability of databases and knowledge graphs for a wider range of applications.
Papers
Discursive objection strategies in online comments: Developing a classification schema and validating its training
Ashley L. Shea, Aspen K. B. Omapang, Ji Yong Cho, Miryam Y. Ginsparg, Natalie Bazarova, Winice Hui, René F. Kizilcec, Chau Tong, Drew Margolin
MCS-SQL: Leveraging Multiple Prompts and Multiple-Choice Selection For Text-to-SQL Generation
Dongjun Lee, Choongwon Park, Jaehyuk Kim, Heesoo Park