NLG Platform Using Composable Goals for Narrative Generation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional natural language generation (NLG) systems face limitations in communicating data-driven ideas, with constraints on variability in word choice and limited capabilities in analyzing data sets to determine content for narrative stories, leading to restricted narrative generation.
Innovation Solution
The development of a narrative generation platform using composable communication goal statements and ontologies allows users to generate narrative stories without direct coding, enabling flexible and reusable knowledge bases for various domains, with the ability to adapt content and structure based on data analysis through a conditional outcome framework.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional template approaches are used for NLG, then system simplicity is maintained, but narrative variability and data analysis capability are limited
Solution Approach 1:
The system segments the NLG process into distinct modules: data analysis module, communication goal determination module, and narrative generation module. Each module handles specific tasks independently, allowing the system to achieve high adaptability through modular components while maintaining manageable overall complexity through clear separation of concerns.
Solution Approach 2:
The system implements dynamic adaptability where the narrative generation process adjusts based on data analysis results and determined communication goals. The system can dynamically select from multiple narrative templates and adjust word choice variability based on the specific data set and communication objectives, rather than using fixed static templates.
2Adaptability or versatility
If conventional template approaches are used for NLG, then ease of operation is maintained, but data analysis capability and content determination are limited
Solution Approach 1:
The system introduces an intermediary layer between raw data and narrative output: the communication goal determination module. This intermediary analyzes data sets, identifies key insights, and determines appropriate communication goals before narrative generation, enabling sophisticated data analysis capability while keeping the user interface simple through automated goal determination.
Solution Approach 2:
The system implements self-service through automated data analysis and communication goal determination. The AI automatically analyzes data sets, identifies important patterns, and determines what communication goals should be achieved, reducing the need for users to have programming expertise while maintaining high adaptability to different data types and analysis requirements.
3Ease of operation
If conventional NLG systems are used, then programming expertise requirement is reduced, but narrative generation robustness and adaptability are limited
Solution Approach 1:
The system implements feedback loops where the data analysis results inform communication goal determination, which in turn guides narrative generation. The system continuously refines its output based on feedback from data analysis quality and communication goal achievement, ensuring robust narrative generation while maintaining ease of use through automated iterative improvement.
Solution Approach 2:
The system changes key parameters dynamically: instead of fixed templates, it uses variable narrative structures selected based on data characteristics and communication goals. Word choice variability, sentence structure, and narrative focus are adjusted as parameters based on the specific data set and determined communication objectives, achieving robustness without requiring programming expertise from users.
Data Source
AI summary
Artificial intelligence (AI) technology can be used in combination with composable communication goal statements to facilitate a user's ability to quickly structure story outlines using “analyze” communication goals in a manner usable by an NLG narrative generation system without any need for the user to directly author computer code. This AI technology permits NLG systems to determine the appropriate content for inclusion in a narrative story about a data set in a manner that will satisfy a desired analysis communication goal such that the narratives will express various ideas that are deemed relevant to a given analysis communication goal.