Conversation space artifact generation using natural language processing, machine learning, and ontology-based techniques

1. A method, in a data processing system comprising a processor and a memory, the memory comprising instructions that are executed by the processor to specifically configure the processor to implement a conversational system artifact generation, the method comprising:

receiving, by a middleware component of the conversational system, a user input;

determining, by the middleware component, whether there is sufficient information in the user input and a conversation space in a context storage of the conversational system to identify user intent associated with the user input, wherein the conversation space includes intents, entities, dialog, and context for a given interaction with the user;

responsive to the middleware component determining there is not sufficient information to identify user intent, sending, by a communications handler component within the conversational system, a natural language query to an external data source via a natural language query (NLQ) interface;

receiving, by the communications handler component, a natural language response from the external data source;

updating, by the middleware component, the conversation space based on the natural language response; and

returning, by the middleware component, a user response based on the natural language response.

2. The method of claim 1 , further comprising updating, by a reasoner component within the conversational system, structured query templates based on the natural language response.

3. The method of claim 2 , further comprising:

responsive to the middleware component determining there is sufficient information to identify user intent, generating, by a reasoner component within the conversational system, a structured query based on the structured query templates;

sending, by the middleware component, the structured query to the communications handler component; and

sending, by the communications handler component, the structured query to the external data source; and

receiving, by the communications handler component, a structured query response from the external data source.

4. The method of claim 1 , further comprising:

generating query templates to be associated with intents for the conversational system based on an ontology, a domain corpus of documents, and prior user questions; and

storing the query templates in a structured query template storage.

5. The method of claim 4 , wherein generating the query templates comprises:

identifying key concepts in a domain ontology that represent common domain entities;

identifying dependent concepts in the domain ontology that are concepts in an immediate neighborhood of the key concepts;

identifying workload patterns around pairs of key concepts and dependent concepts; and

generating the query templates for the identified workload patterns.

6. The method of claim 4 , wherein generating the query templates comprises generating the query templates using regular expressions.

7. The method of claim 4 , wherein generating the query templates comprises:

using natural language processing and machine learning techniques to identify entities and usage patterns over the domain corpus of documents and the prior user questions;

generating the query templates for the identified entities and usage patterns.

8. The method of claim 1 , wherein updating the conversation space comprises:

extracting a new intent and one or more new entities from the natural language response;

dynamically generating a new dialog that responds to the new intent; and

adding the new intent, the one or more new entities, and the new dialog to the conversation space.

9. A computer program product comprising a computer readable storage medium having a computer readable program stored therein, wherein the computer readable program, when executed on a processor of a data processing system, causes the data processing system to implement a conversational system with artifact generation, wherein the computer readable program causes the data processing system to:

receive, by a middleware component of the conversational system, a user input;

determine, by the middleware component, whether there is sufficient information in the user input and a conversation space in a context storage of the conversational system to identify user intent associated with the user input, wherein the conversation space includes intents, entities, dialog, and context for a given interaction with the user;

responsive to the middleware component determining there is not sufficient information to identify user intent, send, by a communications handler component within the conversational system, a natural language query to an external data source via a natural language query (NLQ) interface;

receive, by the communications handler component, a natural language response from the external data source;

update, by the middleware component, the conversation space based on the natural language response; and

return, by the middleware component, a user response based on the natural language response.

10. The computer program product of claim 9 , wherein the computer readable program further causes the data processing system to update, by a reasoner component within the conversational system, structured query templates based on the natural language response.

11. The computer program product of claim 10 , wherein the computer readable program further causes the data processing system to:

responsive to the middleware component determining there is sufficient information to identify user intent, generate, by a reasoner component within the conversational system, a structured query based on the structured query templates;

send, by the middleware component, the structured query to the communications handler component; and

send, by the communications handler component, the structured query to the external data source; and

receive, by the communications handler component, a structured query response from the external data source.

12. The computer program product of claim 9 , wherein the computer readable program further causes the data processing system to:

generate query templates to be associated with intents for the conversational system based on an ontology, a domain corpus of documents, and prior user questions; and

store the query templates in a structured query template storage.

13. The computer program product of claim 12 , wherein generating the query templates comprises:

identifying key concepts in a domain ontology that represent common domain entities;

identifying dependent concepts in the domain ontology that are concepts in an immediate neighborhood of the key concepts;

identifying workload patterns around pairs of key concepts and dependent concepts; and

generating the query templates for the identified workload patterns.

14. The computer program product of claim 12 , wherein generating the query templates comprises generating the query templates using regular expressions.

15. The computer program product of claim 12 , wherein generating the query templates comprises:

using natural language processing and machine learning techniques to identify entities and usage patterns over the domain corpus of documents and the prior user questions;

generating the query templates for the identified entities and usage patterns.

16. The computer program product of claim 9 , wherein updating the conversation space comprises:

extracting a new intent and one or more new entities from the natural language response;

dynamically generating a new dialog that responds to the new intent; and

adding the new intent, the one or more new entities, and the new dialog to the conversation space.

17. An apparatus comprising:

a processor; and

a memory coupled to the processor, wherein the memory comprises instructions which, when executed by the processor, cause the processor to implement a conversational system with artifact generation, wherein the instructions cause the processor to:

receive, by a middleware component of the conversational system, a user input;

determine, by the middleware component, whether there is sufficient information in the user input and a conversation space in a context storage of the conversational system to identify user intent associated with the user input, wherein the conversation space includes intents, entities, dialog, and context for a given interaction with the user;

responsive to the middleware component determining there is not sufficient information to identify user intent, send, by a communications handler component within the conversational system, a natural language query to an external data source via a natural language query (NLQ) interface;

receive, by the communications handler component, a natural language response from the external data source;

update, by the middleware component, the conversation space based on the natural language response; and

return, by the middleware component, a user response based on the natural language response.

18. The apparatus of claim 17 , wherein the instructions further cause the processor to:

update, by a reasoner component within the conversational system, structured query templates based on the natural language response;

responsive to the middleware component determining there is sufficient information to identify user intent, generate, by a reasoner component within the conversational system, a structured query based on the structured query templates;

send, by the middleware component, the structured query to the communications handler component; and

send, by the communications handler component, the structured query to the external data source; and

receive, by the communications handler component, a structured query response from the external data source.

19. The apparatus of claim 17 , wherein the instructions further cause the processor to:

generate query templates to be associated with intents for the conversational system based on an ontology, a domain corpus of documents, and prior user questions; and

store the query templates in a structured query template storage.

20. The apparatus of claim 17 , wherein updating the conversation space comprises:

extracting a new intent and one or more new entities from the natural language response;

dynamically generating a new dialog that responds to the new intent; and

adding the new intent, the one or more new entities, and the new dialog to the conversation space.