AI Narrative Generation Using Composable Explanation Goals
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional natural language generation (NLG) systems face limitations in communicating data-driven ideas per sentence, variability in word choice, and analyzing data sets to determine content presentation, constraining their narrative generation capabilities.
Innovation Solution
The use of composable communication goal statements and ontologies allows users to structure story outlines without coding, with the ontology serving as a reusable knowledge-base for generating narratives, and the system adapting 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 to translate data into text, then the generation process is simple and structured, but the system is constrained in how many data-driven ideas can be communicated per sentence and has limited variability in word choice
Solution Approach 1:
The system segments the narrative generation process into distinct modules: data analysis module, communication goal determination module, and natural language generation module. Each module handles specific aspects of the generation process independently, allowing flexibility in narrative content while maintaining manageable system architecture through modular design
Solution Approach 2:
The system dynamically adapts communication goals and narrative content based on analyzed data sets. The communication goals are determined through AI analysis of data characteristics, enabling the system to adjust sentence structure, word choice, and content emphasis according to the actual data being processed, thereby achieving flexibility without fixed templates
2Productivity
If conventional NLG systems are used, then the basic translation from data to text is achieved, but the systems lack advanced capabilities in analyzing data sets to determine the content that should be presented to a reader
Solution Approach 1:
The system performs preliminary AI-based analysis of data sets before generating narratives. This preliminary action includes analyzing data characteristics, identifying key insights, and determining communication goals in advance. By preparing the analysis phase beforehand, the subsequent narrative generation process becomes more efficient and targeted, improving productivity while the analysis complexity is contained in a dedicated module
3Adaptability or versatility
If users want to structure story outlines using ontologies, then narrative generation capability is enhanced, but users need programming knowledge to implement the system
Solution Approach 1:
The system introduces an intermediary layer between the user and the underlying technical components. Users interact with high-level abstractions such as communication goals and ontologies through intuitive interfaces, while the system automatically handles the complex mapping to technical implementations. This intermediary layer enables users without programming knowledge to leverage enhanced narrative generation capabilities
Solution Approach 2:
The system provides self-service functionality where the AI components automatically determine communication goals and generate appropriate narratives based on user inputs and analyzed data. The system serves itself by handling complex processing tasks autonomously, eliminating the need for users to write code or configure technical parameters while still enabling sophisticated narrative generation
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 “explanation” 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 explanation communication goal such that the narratives will express various ideas that are deemed relevant to a given explanation communication goal.