Semantic space configuration
Representing in a database, a collection of items characterized by features. In a data processing system, determining a semantic space representations of the features across the collection. Each representation characterized by parameters and settings, and differing from each other by only one of: the value of one parameter, and the configuration of one setting. Determining, for each feature pair of a set of feature pairs, the relatedness of the first feature to the second feature in each semantic space representation. And representing the collection by the semantic space that provides the best aggregate relatedness across the set of feature pairs.
1. A method of representing in a database, a collection of items characterized by features, the method comprising:
in a data processing system:
determining a plurality of semantic space representations of the features across the collection, each semantic space representation:
characterized by parameters and settings, and
differing from each other by only one of:
the value of one parameter, and
the configuration of one setting;
determining, for each feature pair of a set of feature pairs, the relatedness of the first feature to the second feature in each semantic space representation;
representing the collection by the semantic space representation that provides the best aggregate relatedness across the set of feature pairs.
2. The method of claim 1 , wherein:
the relatedness of the first feature to the second feature is determined as rank of the second feature in response to a query comprising the first feature into each semantic space representation.
3. The method of claim 2 , wherein:
the aggregate relatedness is measured as the average determined rank.
4. The method of claim 1 , wherein:
each semantic space representation differs from each other semantic space representation by the value of dimensionality k.
5. A computer program product for representing in a database, a collection of items characterized by features, the computer program product comprising:
the non-transitory computer readable media, and
programming modules:
stored on the non-transitory media, and
operative, when executed in a data processing system to:
determine a plurality of semantic space representations of the features across the collection, each semantic space representation:
characterized by parameters and settings, and differing from each other by only one of:
the value of one parameter, and the configuration of one setting;
determine, for each feature pair of a set of feature pairs, the relatedness of the first feature to the second feature in each semantic space representation;
represent the collection by the semantic space representation that provides the best aggregate relatedness across the set of feature pairs.
6. The computer program product of claim 5 , wherein:
the relatedness of the first feature to the second feature is determined as rank of the second feature in response to a query comprising the first feature into each semantic space representation.
7. The computer program product of claim 6 , wherein:
the aggregate relatedness is measured as the average determined rank.
8. The computer program product of claim 5 , wherein each semantic space representation differs from each other representation by the value of dimensionality k.