System and method for proposing annotations
Systems, methods and computer program code to propose annotations are provided which include identifying an input, applying a grouping model to the input to predict at least a first grouping concept associated with the input, comparing the at least first grouping concept to a set of relationship data to select at least a first ranking model, applying the at least first ranking model to the input to predict at least a first ranking concept associated with the input, and causing a user interface to display the input, the at least first grouping concept and the at least first ranking concept to a user as proposed annotations of the input.
1. A computer implemented method to propose annotations, comprising:
identifying an input;
applying a first machine learning model to the input to predict at least a first grouping concept associated with the input;
comparing the at least first grouping concept to a set of relationship data to select at least a second machine learning model based on a relationship between the at least first grouping concept and the second machine learning model;
applying the at least second machine learning model to the input to predict at least a first ranking concept associated with the input; and
causing a user interface to display the input and the at least first grouping concept to a user as proposed annotations of the input.
2. The computer implemented method of claim 1 , wherein the first machine learning model is a classification model trained to recognize at least a first grouping concept in an input.
3. The computer implemented method of claim 1 , wherein the at least second machine learning model is a classification model trained to recognize at least a first ranking concept in an input.
4. The computer implemented method of claim 3 , wherein the at least second machine learning model has a predefined relationship to the at least first grouping concept.
5. The computer implemented method of claim 1 , wherein the first machine learning model further predicts at least a second grouping concept associated with the input, the method further comprising:
comparing the at least second grouping concept to the set of relationship data to select at least a third machine learning model based on a relationship between the at least second grouping concept and the third machine learning model; and
applying the at least third machine learning model to the input to predict at least a second ranking concept associated with the input.
6. The computer implemented method of claim 5 , wherein the causing the user interface to display further comprises:
causing the user interface to display the at least second ranking concept.
7. The computer implemented method of claim 1 , wherein applying the first machine learning model to the input further comprises predicting a plurality of grouping concepts associated with the input.
8. The computer implemented method of claim 7 , wherein applying the at least second machine learning model to the input further comprises predicting a plurality of ranking concepts associated with the input.
9. The computer implemented method of claim 8 , further comprising:
filtering the plurality of grouping concepts and the plurality of ranking concepts to select a set of concepts for display to the user.
10. The computer implemented method of claim 9 , wherein the filtering is based on a confidence score associated with each one of the plurality of grouping concepts and each one of the plurality of ranking concepts.
11. The computer implemented method of claim 1 , further comprising:
receiving an input from the user selecting at least one of the first grouping concept and the at least first ranking concept as an annotation.
12. The computer implemented method of claim 11 , further comprising:
storing information associated with the annotation in association with the input.
13. The computer implemented method of claim 1 , further comprising:
receiving an input from the user to create a new relationship based on selecting at least one of the first grouping concept and the at least first ranking concept.
14. The computer implemented method of claim 13 , further comprising:
prompting the user to identify a type of the relationship; and
updating the set of relationship data to include the new relationship and the type of the relationship.
15. The computer implemented method of claim 14 , wherein the type is relationship is one of a child relationship, a parent relationship and a synonym relationship.
16. A system comprising:
a processing unit; and
a memory storage device including program code that when executed by the processing unit causes to the system to:
applying a first machine learning model to an input to predict at least a first grouping concept associated with the input;
comparing the at least first grouping concept to a set of relationship data to select at least a second machine learning model based on a relationship between the at least first grouping concept and the second machine learning model;
applying the at least second machine learning model to the input to predict at least a first ranking concept associated with the input; and
causing a user interface to display the input, the at least first grouping concept and the at least first ranking concept to a user as proposed annotations of the input.
17. The system of claim 16 , wherein the causing the user interface to display further comprises:
causing the user interface to display the at least second ranking concept.
18. The system of claim 16 , wherein applying the first machine learning model to the input further comprises predicting a plurality of grouping concepts associated with the input.
19. The system of claim 18 , wherein applying the at least second machine learning model to the input further comprises predicting a plurality of ranking concepts associated with the input.
20. The system of claim 19 , further comprising:
filtering the plurality of grouping concepts and the plurality of ranking concepts to select a set of concepts for display to the user.