Resolving textual numerical queries using natural language processing techniques

1. A computer-implemented method, comprising:

determining (i) each of one or more variables with a stated numerical value in a textual query and (ii) each of one or more variables without a stated numerical value in the textual query by performing semantic analysis on the textual query;

normalizing each of the stated numerical values corresponding to one or more of the determined variables by automatically converting each of the stated numerical values corresponding to the one or more of the determined variables to a pre-determined canonical form, wherein said normalizing comprises processing one or more value measurement categories (i) associated with the stated numerical values and (ii) represented by natural language in the textual query;

mapping (i) all of the determined variables and (ii) the normalized values corresponding to the one or more of the determined variables to a pre-defined dependency formulae graph; and

generating a solution to the textual query by automatically computing a numerical value for each of the one or more determined variables without a stated numerical value by implementing a graphical model inference mechanism against the pre-defined dependency formula graph subsequent to said mapping, wherein said implementing the graphical model inference mechanism comprises inferring application of one or more distinct formulae among the pre-defined dependency formulae graph related to computing a numerical value for each of the one or more determined variables without a stated numerical value;

wherein the steps are carried out by at least one computing device.

2. The computer-implemented method of claim 1 , wherein said performing semantic analysis comprises automatically identifying one or more functional mathematical terms in the textual query.

3. The computer-implemented method of claim 2 , wherein said one or more functional mathematical terms comprise at least one of the terms selected from the group consisting of (i) an addition term, (ii) a subtraction term, (iii) a multiplication term, and (iv) a division term.

4. The computer-implemented method of claim 1 , wherein said performing semantic analysis comprises automatically identifying one or more synonyms of functional mathematical terms in the textual query.

5. The computer-implemented method of claim 1 , wherein said one or more value measurement categories comprise at least one element selected from the group consisting of (i) height, (ii) width, (iii) length, (iv) distance, (v) area, (vi) surface area, (vii) velocity, and (viii) temperature.

6. The computer-implemented method of claim 1 , wherein said normalizing comprises applying one or more unit conversion formulae to the stated numerical values.

7. A computer program product, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a device to cause the device to:

determine (i) each of one or more variables with a stated numerical value in a textual query and (ii) each of one or more variables without a stated numerical value in the textual query by performing semantic analysis on the textual query;

normalize each of the stated numerical values corresponding to one or more of the determined variables by automatically converting each of the stated numerical values corresponding to the one or more of the determined variables to a pre-determined canonical form, wherein said normalizing comprises processing one or more value measurement categories (i) associated with the stated numerical values and (ii) represented by natural language in the textual query;

map (i) all of the determined variables and (ii) the normalized values corresponding to the one or more of the determined variables to a pre-defined dependency formulae graph; and

generate a solution to the textual query by automatically computing a numerical value for each of the one or more determined variables without a stated numerical value by implementing a graphical model inference mechanism against the pre-defined dependency formula graph subsequent to said mapping, wherein said implementing the graphical model inference mechanism comprises inferring application of one or more distinct formulae among the pre-defined dependency formulae graph related to computing a numerical value for each of the one or more determined variables without a stated numerical value.

8. The computer program product of claim 7 , wherein said performing semantic analysis comprises automatically identifying one or more functional mathematical terms in the textual query.

9. The computer program product of claim 7 , wherein said performing semantic analysis comprises automatically identifying one or more synonyms of functional mathematical terms in the textual query.

10. The computer program product of claim 7 , wherein said normalizing comprises applying one or more unit conversion formulae to the stated numerical values.

11. A system comprising:

a memory; and

at least one processor coupled to the memory and configured for:

determining (i) each of one or more variables with a stated numerical value in a textual query and (ii) each of one or more variables without a stated numerical value in the textual query by performing semantic analysis on the textual query;

normalizing each of the stated numerical values corresponding to one or more of the determined variables by automatically converting each of the stated numerical values corresponding to the one or more of the determined variables to a pre-determined canonical form, wherein said normalizing comprises processing one or more value measurement categories (i) associated with the stated numerical values and (ii) represented by natural language in the textual query;

mapping (i) all of the determined variables and (ii) the normalized values corresponding to the one or more of the determined variables to a pre-defined dependency formulae graph; and

generating a solution to the textual query by automatically computing a numerical value for each of the one or more determined variables without a stated numerical value by implementing a graphical model inference mechanism against the pre-defined dependency formula graph subsequent to said mapping, wherein said implementing the graphical model inference mechanism comprises inferring application of one or more distinct formulae among the pre-defined dependency formulae graph related to computing a numerical value for each of the one or more determined variables without a stated numerical value.

12. A computer-implemented method, comprising:

generating a domain-specific dependency formulae graph for each of multiple domains based on a collection of pre-defined formulae;

determining (i) each of one or more variables with a stated numerical value in a textual query and (ii) each of one or more variables without a stated numerical value in the textual query by performing semantic analysis on the textual query;

normalizing each of the stated numerical values corresponding to one or more of the determined variables by automatically converting each of the stated numerical values corresponding to the one or more of the determined variables to a pre-determined canonical form, wherein said normalizing comprises processing one or more value measurement categories (i) associated with the stated numerical values and (ii) represented by natural language in the textual query;

selecting one of the multiple generated domain-specific dependency formulae graphs based on the determined variables in the textual query;

mapping (i) all of the determined variables and (ii) the normalized values corresponding to one or more of the determined variables to the selected dependency formulae graph; and

generating a solution to the textual query by automatically computing a numerical value for each of the one or more determined variables without a stated numerical value by implementing a graphical model inference mechanism against the selected pre-defined dependency formula graph subsequent to said mapping, wherein said implementing the graphical model inference mechanism comprises inferring application of one or more distinct formulae among the pre-defined dependency formulae graph related to computing a numerical value for each of the one or more determined variables without a stated numerical value;

wherein the steps are carried out by at least one computing device.

13. The computer-implemented method of claim 12 , comprising:

grouping multiple subsets of vertices into a clique for each of the generated dependency formulae graphs, wherein said grouping is based on the variables of the corresponding formulae, and wherein the vertices represent the variables.

14. The computer-implemented method of claim 12 , wherein said performing semantic analysis comprises automatically identifying one or more functional mathematical terms in the textual query.

15. The computer-implemented method of claim 14 , wherein said one or more functional mathematical terms comprise at least one of the terms selected from the group consisting of (i) an addition term, (ii) a subtraction term, (iii) a multiplication term, and (iv) a division term.

16. The computer-implemented method of claim 12 , wherein said performing semantic analysis comprises automatically identifying one or more synonyms of functional mathematical terms in the textual query.