Enhancing factualness and controllability of Data-to-Text Generation via data Views and constraints
Craig Thomson, Clément Rebuffel, Ehud Reiter, Laure Soulier, Somayajulu Gowri Sripada, Patrick Gallinari · 2023
Neural data-to-text systems lack the control and factual accuracy required to generate useful and insightful summaries of multidimensional data.We propose a solution in the form of data views, where each view describes an entity and its attributes along specific dimensions.A sequence of views can then be used as a high-level schema for document planning, with the neural model handling the complexities of micro-planning and surface realization.We show that our view-based system retains factual accuracy while offering high-level control of output that can be tailored based on user preference or other norms within the domain.