Adapting dialog models by relevance value for concepts to complete a task

1. An apparatus comprising:

at least one processor;

at least one memory including computer program code;

the at least one memory and the computer program code being configured to, with the at least one processor, cause the apparatus at least to:

identify one or more relevant concepts from a document, the one or more relevant concepts comprising information relevant to completing a task;

obtain conversation turns in association with a dialog to be included in a dialog model to be used for completing the task;

compute a relevance value of one or more utterances of the conversation turns with respect to completing the task using the one or more relevant concepts;

assign summary labels to the conversation turns in the dialog based on the relevance values computed for the one or more utterances of the conversation turns, the summary labels identifying conversation management turns and information management turns, the conversation management turns comprising one or more utterances that are considered non-essential with respect to completing the task, the information management turns comprising one or more utterances that are considered essential with respect to completing the task; and

remove one or more utterances associated with a given conversation management turn from the dialog model when the relevance value of the one or more utterances is determined to be below a given threshold value.

2. The apparatus of claim 1 , wherein identifying the one or more relevant concepts from the document comprises a graph-based decomposition process.

3. The apparatus of claim 2 , wherein computing the relevance value comprises determining a measure of centrality associated with a text graph.

4. The apparatus of claim 1 , wherein identifying the one or more relevant concepts from the document further comprises computation of one or more of a term frequency, an inverse document frequency, and a term frequency-inverse document frequency.

5. The apparatus of claim 1 , wherein the one or more relevant concepts comprise one or more of linguistic constituents and tokens.

6. The apparatus of claim 1 , wherein computing the relevance value further comprises computing one or more of a maximum marginal relevance value, an integer linear programming value, and a sequential minimal optimization value.

7. The apparatus of claim 1 wherein assigning summary labels to the conversation turns includes utilizing Boolean type labels to identify the conversation management turns and the information management turns.

8. A computer-implemented method comprising:

identifying one or more relevant concepts from a document, the one or more relevant concepts comprising information relevant to completing a task;

obtaining conversation turns in association with a dialog to be included in a dialog model to be used for completing the task;

computing a relevance value of one or more utterances of the conversation turns with respect to completing the task using the one or more relevant concepts;

assigning summary labels to the conversation turns in the dialog based on the relevance values computed for the one or more utterances of the conversation turns, the summary labels identifying conversation management turns and information management turns, the conversation management turns comprising one or more utterances that are considered non-essential with respect to completing the task, the information management turns comprising one or more utterances that are considered essential with respect to completing the task; and

removing one or more utterances associated with a given conversation management turn from the dialog model when the relevance value of the one or more utterances is determined to be below a given threshold value.

9. The method of claim 8 , wherein identifying the one or more relevant concepts from the document further comprises a graph-based decomposition process.

10. The method of claim 9 , wherein computing the relevance value comprises determining a measure of centrality associated with a text graph.

11. The method of claim 8 , wherein identifying the one or more relevant concepts from the document further comprises computation of one or more of a term frequency, an inverse document frequency, and a term frequency-inverse document frequency.

12. The method of claim 8 , wherein the one or more relevant concepts comprise one or more of linguistic constituents and tokens.

13. The method of claim 8 , wherein computing the relevance value further comprises computing one or more of a maximum marginal relevance value, an integer linear programming value, and a sequential minimal optimization value.

14. The method of claim 8 , wherein assigning summary labels to the conversation turns includes utilizing Boolean type labels to identify the conversation management turns and the information management turns.

15. An article of manufacture comprising a non-transitory computer-readable storage medium having embodied therein executable program code that when executed by a processor causes the processor to perform steps of:

identifying one or more relevant concepts from a document, the one or more relevant concepts comprising information relevant to completing a task;

obtaining conversation turns in association with a dialog to be included in a dialog model to be used for completing the task;

computing a relevance value of one or more utterances of the conversation turns with respect to completing the task using the one or more relevant concepts;

assigning summary labels to the conversation turns in the dialog based on the relevance values computed for the one or more utterances of the conversation turns, the summary labels identifying conversation management turns and information management turns, the conversation management turns comprising one or more utterances that are considered non-essential with respect to completing the task, the information management turns comprising one or more utterances that are considered essential with respect to completing the task; and

removing one or more utterances associated with a given conversation management turn from the dialog model when the relevance value of the one or more utterances is determined to be below a given threshold value.

16. The article of claim 15 , wherein identifying the one or more relevant concepts from the document comprises a graph-based decomposition process.

17. The article of claim 16 , wherein computing the relevance value comprises determining a measure of centrality associated with a text graph.

18. The article of claim 15 , wherein identifying the one or more relevant concepts from the document further comprises computation of one or more of a term frequency, an inverse document frequency, and a term frequency-inverse document frequency.

19. The article of claim 15 , wherein the one or more relevant concepts comprise one or more of linguistic constituents and tokens.

20. The article of claim 15 , wherein computing the relevance value further comprises computing one or more of a maximum marginal relevance value, an integer linear programming value, and a sequential minimal optimization value.