NLG Automatability Assessment for Document Segments
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Natural Language Generation (NLG) systems are not well-suited to generate every type of document, requiring time-consuming configuration for specific tasks, and there is a need to determine the automatability of document generation using existing NLG systems to optimize effort and focus on non-automatable segments.
Innovation Solution
A method and system that determine the degree to which a document can be generated using an NLG system by obtaining a document, identifying text segments, generating annotated representations, and calculating similarity measures between these representations and pre-existing NLG-generated text to assess the suitability of semantic objects for automatic text generation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If an NLG system is used to generate documents, then productivity is improved, but device complexity increases due to configuration requirements
Solution Approach 1:
The system performs preliminary analysis of the target document structure and content requirements before attempting generation. By pre-assessing whether the document type matches the NLG system's capabilities, the system avoids unnecessary configuration efforts and identifies suitable semantic objects in advance, thereby reducing configuration complexity while maintaining productivity benefits
Solution Approach 2:
The system segments the document into text segments and evaluates each segment's automatability independently. This segmentation allows the system to identify which portions can be generated automatically versus which require manual intervention, reducing the overall configuration burden by focusing only on suitable segments
2Adaptability or versatility
If the NLG system configures itself for specific tasks, then adaptability is improved, but loss of time increases due to configuration requirements
Solution Approach 1:
The system performs self-assessment by automatically analyzing the target document and determining its own suitability for generating that document type. This self-service capability eliminates the need for manual configuration time while maintaining adaptability, as the system independently identifies compatible semantic objects and generation approaches
Solution Approach 2:
The system performs preliminary compatibility assessment between the target document and available semantic objects before actual generation. This pre-evaluation step enables quick determination of adaptability without requiring time-consuming configuration, as the system pre-identifies suitable semantic objects based on document structure and content analysis
Data Source
AI summary
Techniques for determining a degree to which a document can be generated using a natural language generation (NLG) system, the NLG system being configured to generate natural language text. The techniques include using at least one computer hardware processor to perform: obtaining a document including text segments; determining a degree to which at least some of the text segments can be generated using the NLG system; generating a report indicating the degree to which the at least some of the text segments can be generated using the NLG system; and outputting the report.