Generating a candidate set of entities from a training set

1. A method for generating a candidate set of entities from a training set of entities, the method comprising:

determining an ontology class for an input entity in the training set of entities, wherein the input entity is inputted into an interface for the method;

adding the input entity to an ontology list;

assigning an entity score to the input entity;

normalizing the ontology list of entity scores; and

selecting the candidate set of entities with the lowest entity score, wherein the candidate set of entities includes a most similar entity to the input entity, and wherein the most similar entity and the input entity are not identified based on co-occurrence in any known documents.

2. The method of claim 1 , wherein adding the input entity to the ontology list further comprises:

grouping one or more input entities based on the ontology class.

3. The method of claim 1 , wherein the entity score is equal to a sum of an inverse of the ontology class size.

4. The method of claim 1 , further comprising:

summing the entity scores of an entity determined to exist in more than one ontology class.

5. The method of claim 1 , wherein normalizing the ontology list of entity scores further comprises:

removing the input entity from a scored set of input entities;

assigning a metric to the input entity;

generating a set of ranked lists for the scored set of input entities; and

merging the set of ranked lists by selecting a lowest metric for the input entity to add to the candidate set of entities, wherein a highest ranked gene from each of the set of ranked lists is retained to comprise the candidate set of entities.

6. The method of claim 5 , wherein assigning a metric to the input entity further comprises:

determining a number of entities above the input entity in a sorted list.

7. The method of claim 6 , further comprising:

selecting an input entity with a lowest metric based on the input entity existing in more than one ontology class.

8. A computer system for generating a candidate set of entities from a training set of entities, comprising:

one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage medium, and program instructions stored on at least one of the one or more tangible storage medium for execution by at least one of the one or more processors via at least one of the one or more memories, wherein the computer system is capable of performing a method comprising:

determining an ontology class for an input entity in the training set of entities, wherein the input entity is inputted into an interface for the method;

adding the input entity to an ontology list;

assigning an entity score to the input entity;

normalizing the ontology list of entity scores; and

selecting the candidate set of entities with the lowest entity score, wherein the candidate set of entities includes a most similar entity to the input entity, and wherein the most similar entity and the input entity are not identified based on co-occurrence in any known documents.

9. The computer system of claim 8 , wherein adding the input entity to the ontology list further comprises:

grouping one or more input entities based on the ontology class.

10. The computer system of claim 8 , wherein the entity score is equal to a sum of an inverse of the ontology class size.

11. The computer system of claim 8 , further comprising:

summing the entity scores of an entity determined to exist in more than one ontology class.

12. The computer system of claim 8 , wherein normalizing the ontology list of entity scores further comprises:

removing the input entity from a scored set of input entities;

assigning a metric to the input entity;

generating a set of ranked lists for the scored set of input entities; and

merging the set of ranked lists by selecting a lowest metric for the input entity to add to the candidate set of entities, wherein a highest ranked gene from each of the set of ranked lists is retained to comprise the candidate set of entities.

13. The computer system of claim 12 , wherein assigning a metric to the input entity further comprises:

determining a number of entities above the input entity in a sorted list.

14. The computer system of claim 13 , further comprising:

selecting an input entity with a lowest metric based on the input entity existing in more than one ontology class.

15. A computer program product for generating a candidate set of entities from a training set of entities, comprising:

one or more non-transitory computer-readable storage media and program instructions stored on at least one of the one or more tangible storage media, the program instructions executable by a processor to cause the processor to perform a method comprising:

determining an ontology class for an input entity in the training set of entities, wherein the input entity is inputted into an interface for the method;

adding the input entity to an ontology list;

assigning an entity score to the input entity;

normalizing the ontology list of entity scores; and

selecting the candidate set of entities with the lowest entity score, wherein the candidate set of entities includes a most similar entity to the input entity, and wherein the most similar entity and the input entity are not identified based on co-occurrence in any known documents.

16. The computer program product of claim 15 , wherein adding the input entity to the ontology list further comprises:

grouping one or more input entities based on the ontology class.

17. The computer program product of claim 15 , wherein the entity score is equal to a sum of an inverse of the ontology class size.

18. The computer program product of claim 15 , further comprising:

summing the entity scores of an entity determined to exist in more than one ontology class.

19. The computer program product of claim 15 , wherein normalizing the ontology list of entity scores further comprises:

removing the input entity from a scored set of input entities;

assigning a metric to the input entity;

generating a set of ranked lists for the scored set of input entities; and

merging the set of ranked lists by selecting a lowest metric for the input entity to add to the candidate set of entities, wherein a highest ranked gene from each of the set of ranked lists is retained to comprise the candidate set of entities.

20. The computer program product of claim 19 , wherein assigning a metric to the input entity further comprises:

determining a number of entities above the input entity in a sorted list.