18318308. ENTITY FOCUSED NATURAL LANGUAGE GENERATION simplified abstract (Oracle International Corporation)
Contents
- 1 ENTITY FOCUSED NATURAL LANGUAGE GENERATION
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 ENTITY FOCUSED NATURAL LANGUAGE GENERATION - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Unanswered Questions
- 1.11 Original Abstract Submitted
ENTITY FOCUSED NATURAL LANGUAGE GENERATION
Organization Name
Oracle International Corporation
Inventor(s)
Praneet Pabolu of Bangalore (IN)
Sriram Chaudhury of Bangalore (IN)
ENTITY FOCUSED NATURAL LANGUAGE GENERATION - A simplified explanation of the abstract
This abstract first appeared for US patent application 18318308 titled 'ENTITY FOCUSED NATURAL LANGUAGE GENERATION
Simplified Explanation
The patent application describes a method for generating natural language sentences based on fake entity values, analyzing the sentences for missing fake values, summarizing the missing values, and generating additional sentences incorporating the missing values.
- Populating fake values for entities
- Generating string of fake entity values
- Inserting sentinel token between fake values
- Generating natural language sentences based on fake values
- Analyzing sentences for missing fake values
- Summarizing missing fake values
- Generating additional sentences with missing values
Potential Applications
This technology could be applied in:
- Automated content generation
- Data validation and verification processes
Problems Solved
This technology helps in:
- Ensuring data completeness and accuracy
- Streamlining natural language generation processes
Benefits
The benefits of this technology include:
- Improved data quality
- Enhanced efficiency in content creation
Potential Commercial Applications
A potential commercial application for this technology could be in:
- Content generation software development
Possible Prior Art
There is no known prior art for this specific method.
Unanswered Questions
How does the method handle complex sentence structures?
The method's ability to handle complex sentence structures is not explicitly mentioned in the abstract. Further details on this aspect would be helpful.
What is the scalability of this method for large datasets?
The abstract does not address the scalability of the method for processing large datasets. Understanding the scalability limitations and capabilities of the technology would be important for practical implementation.
Original Abstract Submitted
Method includes populating fake value for each of entities, to generate string of fake entity values that correspond to entities; inserting sentinel token between adjacent fake values included in the string to generate first input data; generating, by natural language generation model, natural language sentences based on first input data, natural language sentences including one or more fake values from the string; analyzing natural language sentences to determine whether any fake value from the string is missing; based on the fake value missing, summarizing, using text summarization model, natural language sentences to generate text summary; concatenating the text summary with the fake value, to generate second input data; and generating, by a next sentence generation model, additional natural language sentence using the second input data, the additional natural language sentence including the fake value. Additional natural language sentence is combined with natural language sentences to generate final natural language sentences.
