Nonlinear semantic space based on lexical graph
AssigneeHRL Laboratories, LLC
InventorsHankyu Moon, Rajan Bhattacharyya, James Benvenuto
Life of this patent
Estimating the term…
Abstract
Described is a system for generating a semantic space based on the lexical relations between words. The system determines synonym and antonym relations between a set of words. A lexical graph is generated based on the synonym and antonym relations. Manifold embedding of the lexical graph is determined, and Laplacian coordinates of the manifold embedding are assigned as semantic features of the set of words. A quantitative representation of the set of words is generated using the semantic features.
Claims12
A system for generating a semantic space based on the lexical relations between words, the system comprising:
- one or more processors and a non-transitory computer-readable medium having executable instructions encoded thereon such that when executed, the one or more processors perform operations of:
- determining synonym and antonym relations between a set of words;
- generating a lexical graph based on the synonym and antonym relations;
- determining Laplacian embedding of the lexical graph;
- assigning Laplacian coordinates of the Laplacian embedding;
- computing independent component analysis (ICA) coordinates from the Laplacian coordinates, resulting in semantic features for the set of words;
- generating a quantitative representation of the set of words using the semantic features;
- and
- using the quantitative representation, generating control commands for controlling a vehicle control element via a control interface of the vehicle control element.
A computer implemented method for generating a semantic space based on the lexical relations between words, the method comprising an act of:
- causing one or more processors to execute instructions encoded on a non-transitory computer-readable medium, such that upon execution, the one or more processors perform operations of:
- determining synonym and antonym relations between a set of words;
- generating a lexical graph based on the synonym and antonym relations;
- determining Laplacian embedding of the lexical graph;
- assigning Laplacian coordinates of the Laplacian embedding;
- computing independent component analysis (ICA) coordinates from the Laplacian coordinates, resulting in semantic features for the set of words;
- generating a quantitative representation of the set of words using the semantic features;
- and
- using the quantitative representation, generating control commands for controlling a vehicle control element via a control interface of the vehicle control element.
A computer program product for generating a semantic space based on the lexical relations between words, the computer program product comprising:
- a non-transitory computer-readable medium having executable instructions encoded thereon, such that upon execution of the instructions by one or more processors, the one or more processors perform operations of:
- determining synonym and antonym relations between a set of words;
- generating a lexical graph based on the synonym and antonym relations;
- determining Laplacian embedding of the lexical graph;
- assigning Laplacian coordinates of the Laplacian embedding;
- computing independent component analysis (ICA) coordinates from the Laplacian coordinates, resulting in semantic features for the set of words;
- generating a quantitative representation of the set of words using the semantic features;
- and
- using the quantitative representation, generating control commands for controlling a vehicle control element via a control interface of the vehicle control element.
The computer program product as set forth in 9, further comprising instructions for causing the one or more processors to further perform an operation of determining Laplacian eigenvectors of the lexical graph as the Laplacian embedding.
The computer program product as set forth in 9, further comprising instructions for causing the one or more processors to further perform an operation of determining principal components of the lexical graph as the Laplacian embedding.
Dependencies are inferred from the claim text.