Semantic Information
Semantic information, the meaning and relationships within data, is a central focus in numerous research areas, aiming to improve how computers understand and process information beyond simple surface features. Current research emphasizes integrating semantic information into various models, including transformer networks, graph neural networks, and probabilistic graphical models, to enhance tasks like natural language processing, image recognition, and knowledge graph reasoning. This work is significant because improved semantic understanding is crucial for advancing AI capabilities in diverse applications, from more accurate machine translation and question answering to more robust and reliable autonomous systems.
Papers
DynaGRAG: Improving Language Understanding and Generation through Dynamic Subgraph Representation in Graph Retrieval-Augmented Generation
Karishma Thakrar
Generating event descriptions under syntactic and semantic constraints
Angela Cao, Faye Holt, Jonas Chan, Stephanie Richter, Lelia Glass, Aaron Steven White
Is Large Language Model Good at Triple Set Prediction? An Empirical Study
Yuan Yuan, Yajing Xu, Wen Zhang