A knowledge graph-based content selection model for data-driven text generation
Jun Peng Gong, Juan Cao, Peng Zhou Zhang · International Journal of Reasoning-based Intelligent Systems · 2017
Content selection is a critical task for natural language generation. A novel approach based on knowledge graph is proposed. Structure data is mapping to the graph and combined with user defined knowledge. The model analyses the content selection features on the graph, and automatically learns the content selection rules. The model was evaluated in the domain of weather forecasting.