Semantic Ordinal Sorting via Masked Language Model Permutations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Computing systems face difficulty in sorting data based on semantic meaning, often requiring manual encoding of ordinal values, which limits unsupervised data processing and machine learning model performance.
Innovation Solution
A computing system is configured to determine semantic orders of unique values using permutations and masked language models, assigning ordinal values and encoding data for unsupervised sorting, reducing the need for human input and improving machine learning performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual encoding of ordinal values is used for semantic sorting, then sorting accuracy based on semantic meaning is improved, but labor cost and time consumption increase
Solution Approach 1:
The system uses the masked language model to automatically determine semantic orders and generate ordinal values without human intervention. The MLM analyzes the semantic relationships between unique values and autonomously produces the sorting sequence, making the system self-sufficient in eliminating the need for manual encoding while maintaining high sorting accuracy.
Solution Approach 2:
The patent replaces the manual mechanical process of encoding ordinal values with an automated computational process using a masked language model. The MLM processes the unique values and automatically determines their semantic orders, substituting human labor with an intelligent algorithm that achieves both accuracy and efficiency.
2Measurement precision
If manual encoding of ordinal values is used for semantic sorting, then sorting accuracy based on semantic meaning is improved, but automation level decreases
Solution Approach 1:
The system employs the masked language model to autonomously determine semantic orders and generate ordinal values without requiring human operators. The MLM independently analyzes the semantic relationships among unique values and produces the sorting sequence, achieving full automation while maintaining high sorting accuracy through intelligent computational processing.
Solution Approach 2:
The patent replaces the manual encoding process with an automated masked language model that computationally determines semantic orders. This substitution eliminates human intervention entirely, achieving complete automation while maintaining sorting accuracy through the MLM's ability to understand and process semantic relationships between values.
3Productivity
If traditional sorting methods are used, then processing speed is improved, but semantic understanding capability decreases
Solution Approach 1:
The patent replaces traditional mechanical sorting algorithms with a masked language model that possesses semantic understanding capabilities. The MLM processes unique values by comprehending their meanings and relationships, enabling the system to maintain high processing speed while achieving accurate semantic-based sorting that traditional methods cannot accomplish.
Solution Approach 2:
The patent changes the fundamental parameter of how sorting is performed - from rule-based mechanical comparison to semantic-based intelligent processing. By using the MLM to evaluate and compare the semantic meanings of unique values, the system achieves both fast processing and deep semantic understanding, overcoming the limitations of traditional sorting methods.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Operations may include obtaining a dataset that includes a plurality of unique values and obtaining a plurality of permutations with respect to the plurality of unique values. Additionally, the operations may include, for each respective permutation, obtaining a respective overall permutation probability for the respective permutation based on masked value probabilities determined by a masked language model (MLM). Each masked value probability may be determined with respect to a respective masked version of a plurality of masked versions of the respective permutation. The operations may also include selecting a particular permutation from the plurality of permutations based on a comparison between the respective overall permutation probabilities of the plurality of permutations. In addition, the operations may include determining a semantic order of the unique values of the plurality of unique values based on the particular permutation in which the semantic order is related to respective meanings of the unique values.