Method and apparatus for configurable microplanning

1. A method for transforming an input data stream comprising data that is expressed in a non-linguistic format into a format that can be expressed linguistically in a textual output, the method comprising:

accessing a document plan containing one or more messages, wherein messages represent a phrase or a simple sentence and are created in an instance in which the input data stream comprises data that satisfies one or more message requirements;

generating a text specification containing one or more phrase specifications that correspond to the one or more messages in the document plan;

applying, using a processor, a set of lexicalization rules to each of the one or more messages to populate the one or more phrase specifications, wherein the set of lexicalization rules are specified using a microplanning rule specification language that is configured to hide linguistic complexities from a user and comprise a set of message-level rules and a set of slot-level rules; and

realizing the text specification to generate a textual output that linguistically describes at least a portion of the input data stream, wherein the textual output is displayable via a user interface.

2. The method according to claim 1 , wherein the set of lexicalization rules are configured to map content from a message of the one or more messages into a phrase specification of the one or more phrase specifications.

3. The method according to claim 1 , wherein the set of message-level rules apply to the one or more messages and the set of slot-level rules apply to one or more slots that are defined by the one or more messages.

4. The method according to claim 1 , wherein the set of messages level rules comprises one or more rules for each type of message, the one or more rules are configured to indicate how content of the one or more messages of each type of message are to be used to populate one or more elements of the one or more phrase specifications corresponding to each type of message.

5. The method according to claim 1 , wherein the set of message-level rules are configured to assign contents of a slot of a message to particular syntactic constituents in a sentence as defined by an element of a phrase specification.

6. The method according to claim 1 , wherein the microplanning rule specification language is configured to fill syntactic constituents using one or more message-level rules.

7. The method according to claim 6 , wherein the microplanning rule specification language is configured to express the syntactic constituents using at least one of a subject, verb, object, indirect object, front modifier, premodifier or post modifier.

8. The method according to claim 1 , further comprising:

applying one or more reference strategies using one or more slot-level rules, wherein the microplanning rule specification language is configured to expresses reference strategies using at least one of a string value, named entity, numeric value, time value, enumerated value type or duration value.

9. The method according to claim 1 , wherein the microplanning rule specification language is configured to express syntactic constituents using one or more slot-level rules, the microplanning rule specification language is configured to express syntactic constituents within a noun phrase using at least one of a determiner, specifier, noun, modifier, premodifier or post modifier.

10. The method according to claim 1 , wherein one or more message-level rules and one or more slot-level rules are configured such that a genre parameter is able to be overridden.

11. The method according to claim 1 , wherein the text specification is a tree structured object that corresponds to the tree structured object of the document plan.

12. The method according to claim 1 , further comprising:

populating the one or more phrase specifications using one or more genre conventions, wherein the one or more genre conventions are expressed as one or more genre parameters that define a language in a particular genre.

13. The method according to claim 12 , wherein the one or more genre parameters that define the language in the particular genre comprise at least one of a chosen tense, a convention for the use of pronouns or a convention for the use of abbreviations.

14. The method according to claim 1 , further comprising:

aggregating at least two phrases specifications of the one or more phrase specifications based on contents of the at least two phrase specifications, properties of the text specification and the set of lexicalization rules that produced the at least two phrase specifications.

15. The method of claim 1 , further comprising:

applying the set of lexicalization rules by:

identifying one or more correspondences between a structure of the one or more messages and one or more natural language syntactic constituents that are used to express a linguistic output and a structure of the one or more messages.

16. The method according to claim 1 , further comprising:

applying one or more reference strategies.

17. The method according to claim 1 , further comprising:

causing the one or more phrase specifications in the text specification to be output to a realizer.

18. An apparatus that is configured to transform an input data stream comprising data that is expressed in a non-linguistic format into a format that can be expressed linguistically in a textual output, the apparatus comprising:

at least one processor; and

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

access a document plan containing one or more messages, wherein messages represent a phrase or a simple sentence and are created in an instance in which the input data stream comprises data that satisfies one or more message requirements;

generate a text specification containing one or more phrase specifications that correspond to the one or more messages in the document plan;

apply a set of lexicalization rules to each of the one or more messages to populate the one or more phrase specifications, wherein the set of lexicalization rules are specified using a microplanning rule specification language that is configured to hide linguistic complexities from a user and comprise a set of message-level rules and a set of slot-level rules; and

realize the text specification to generate a textual output that linguistically describes at least a portion of the input data stream, wherein the textual output is displayable via a user interface.

19. A computer program product that is configured to transform an input data stream comprising data that is expressed in a non-linguistic format into a format that can be expressed linguistically in a textual output, the computer program product comprising:

at least one computer readable non-transitory memory medium having program code instructions stored thereon, the program code instructions which when executed by an apparatus cause the apparatus at least to:

access a document plan containing one or more messages, wherein messages represent a phrase or a simple sentence and are created in an instance in which the input data stream comprises data that satisfies one or more message requirements;

generate a text specification containing one or more phrase specifications that correspond to the one or more messages in the document plan; and

apply a set of lexicalization rules to each of the one or more messages to populate the one or more phrase specifications, wherein the set of lexicalization rules are specified using a microplanning rule specification language that is configured to hide linguistic complexities from a user and comprise a set of message-level rules and a set of slot-level rules; and

realize the text specification to generate a textual output that linguistically describes at least a portion of the input data stream, wherein the textual output is displayable via a user interface.

20. The method according to claim 1 , wherein a first lexicalization rule is applied to a message at a first instance and a second lexicalization rule is applied to the message at a second instance, wherein the second lexicalization rule results an expression of the message that is distinct from the expression of the message result from the first lexicalization rule.

21. The method according to claim 1 , further comprising:

accessing the one or more rules written in a microplanning rule specification language by a user via the user interface; and

converting the one or more rules into the set of lexicalization comprising the set of message-level rules and the set of slot-level rules.

22. The method according to claim 18 , wherein the set of message-level rules apply to the one or more messages and the set of slot-level rules apply to one or more slots that are defined by the one or more messages.

23. The apparatus according to claim 18 , wherein the set of messages level rules comprises one or more rules for each type of message, the one or more rules are configured to indicate how content of the one or more messages of each type of message are to be used to populate one or more elements of the one or more phrase specifications corresponding to each type of message.

24. The apparatus according to claim 18 , wherein the microplanning rule specification language is configured to express the syntactic constituents using at least one of a subject, verb, object, indirect object, front modifier, premodifier or post modifier.

25. The apparatus according to claim 18 , wherein the at least one memory and the computer program code are further configured to, with the at least one processor, cause the apparatus to at least:

apply one or more reference strategies using one or more slot-level rules, wherein the microplanning rule specification language is configured to expresses reference strategies using at least one of a string value, named entity, numeric value, time value, enumerated value type or duration value.

26. The apparatus according to claim 18 , wherein the microplanning rule specification language is configured to express syntactic constituents using one or more slot-level rules, the microplanning rule specification language is configured to express syntactic constituents within a noun phrase using at least one of a determiner, specifier, noun, modifier, premodifier or post modifier.

27. The apparatus according to claim 18 , wherein the at least one memory and the computer program code are further configured to, with the at least one processor, cause the apparatus to at least:

populate the one or more phrase specifications using one or more genre conventions, wherein the one or more genre conventions are expressed as one or more genre parameters that define a language in a particular genre.

28. The apparatus according to claim 18 , wherein the at least one memory and the computer program code are further configured to, with the at least one processor, cause the apparatus to at least:

aggregate at least two phrases specifications of the one or more phrase specifications based on contents of the at least two phrase specifications, properties of the text specification and the set of lexicalization rules that produced the at least two phrase specifications.

29. The apparatus of claim 18 , wherein the at least one memory and the computer program code are further configured to, with the at least one processor, cause the apparatus to at least apply the set of lexicalization rules by being further configured to:

identify one or more correspondences between a structure of the one or more messages and one or more natural language syntactic constituents that are used to express a linguistic output and a structure of the one or more messages.

30. The apparatus according to claim 18 , wherein the at least one memory and the computer program code are further configured to, with the at least one processor, cause the apparatus to at least:

access the one or more rules written in a microplanning rule specification language by a user via the user interface; and

convert the one or more rules into the set of lexicalization comprising the set of message-level rules and the set of slot-level rules.