Method and apparatus for updating a previously generated text

• US 10,467,333 B2
• Filed: 04/07/2016
• Issued: 11/05/2019
• Est. Priority Date: 08/30/2012
• Status: Active Grant

• Current Assignee: Arria Data2text Limited
• Original Assignee: Arria Data2text Limited
• Inventors: Logan, Alasdair James, Reiter, Ehud Baruch
• Primary Examiner(s): Patel, Manglesh M
• Application Number:
  US15/093,365
• Publication Number:
  US 20160328371A1
• Time in Patent Office: 1,307 Days
• Field of Search: 715200, 715256, 715234, 715264
• CPC Class Codes: G06F 16/353 into predefined classes
• CPC Class Codes: G06F 40/14 Tree-structured documents parsing G06F40/205; validation G06F40/226
• CPC Class Codes: G06F 40/166 Editing, e.g. inserting or deleting
• CPC Class Codes: G06F 40/20 Natural language analysis semantic analysis of natural language G06F40/30

Abstract

Methods, apparatuses, and computer program products are described herein that are configured to enable updating of an output text. In some example embodiments, a method is provided that comprises generating a new message for each updateable data element based on a predetermined indication. The method of this embodiment may also include determining a classification for each new message by comparing each new message with a corresponding message that describes the updateable data element. The method of this embodiment may also include generating an additional document plan tree that contains at least a portion of the new messages. The method of this embodiment may also include combining the additional document plan tree with an original document plan tree.

Claims

1. A method for transforming one or more input data streams that comprise data that is at least partially expressed in a non-linguistic format into a format that can be expressed linguistically in one or more output texts, the method comprising:

generating, using a natural language generation system that is configured to execute on a processor, a first output text based on a set of messages and a relationship between the set of messages, wherein a message represents a phrase or a simple sentence, and is created in an instance in which a first input data stream comprises data that satisfies one or more message requirements;

detecting an updateable data element within a second input data stream, the updateable data element associated with a message of the set of messages, and the second input data stream comprising raw input data that is at least partially expressed in a non-linguistic form;

generating a new message associated with the updateable data element based on a predetermined indication and the second input data stream; and

generating, using the natural language generation system, an updated output text, wherein the updated output text comprises one or more natural language sentences and further comprises at least a portion of the first output text and at least a portion of the new message.

2. A method according to claim 1, wherein the new message is configured to describe the updateable data element over a predetermined time interval.

3. A method according to claim 1, wherein the new message is configured to describe a most significant change in the updateable data element over a predetermined time interval.

4. A method according to claim 1, further comprising determining a classification for the new message by comparing the new message to a corresponding message associated with the first output text.

5. A method according to claim 4, wherein the corresponding message associated with the first output text describes the updateable data element.

6. A method according to claim 1, wherein detecting the updateable data element comprises identifying a state of the second data stream at a time of a triggering event.

7. A method according to claim 1, wherein the predetermined indication comprises a time period of a fixed interval.

8. A method according to claim 1, wherein the predetermined indication comprises a regular interval until an acknowledgement is detected.

9. A method according to claim 1, wherein the predetermined indication is associated with a received request.

10. A method according to claim 1, wherein generating, using the natural language generation system, an updated output text, wherein the updated output text comprises one or more natural language sentences and further comprises at least a portion of the first output text and at least a portion of the new message comprises populating a document plan tree with the new message associated with the updateable data element at a predetermined location within the document plan tree.

11. An apparatus configured to transform or more input data streams that comprise data that is at least partially expressed in a non-linguistic form into a format that can be expressed linguistically in one or more output texts, 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;

generate, via a natural language generation system that is configured to execute on a processor, a first output text based on a set of messages and a relationship between the set of messages, wherein a message represents a phrase or a simple sentence, and is created in an instance in which a first input data stream comprises data that satisfies one or more message requirements;

detect an updateable data element within a second input data stream, the updateable data element associated with a message of the set of messages, and the second input data stream comprising raw input data that is at least partially expressed in a non-linguistic form;

generate a new message associated with the updateable data element based on a predetermined indication and the second input data stream; and

generate, using the natural language generation system, an updated output text, wherein the updated output text comprises one or more natural language sentences and further comprises at least a portion of the first output text and at least a portion of the new message.

12. An apparatus according to claim 11, wherein the new message is configured to describe the updateable data element over a predetermined time interval.

13. An apparatus according to claim 11, wherein the new message is configured to describe a most significant change in the updateable data element over a predetermined time interval.

14. An apparatus according to claim 11, further comprising determining a classification for the new message by comparing the new message to a corresponding message associated with the first output text.

15. An apparatus according to claim 14, wherein the corresponding message associated with the first output text describes the updateable data element.

16. An apparatus according to claim 11, wherein detecting the updateable data element comprises identifying a state of the second data stream at a time of a triggering event.

17. An apparatus according to claim 11, wherein the predetermined indication comprises a time period of a fixed interval or a regular interval until an acknowledgement is detected.

18. An apparatus according to claim 11, wherein the predetermined indication is associated with a received request.

19. An apparatus according to claim 11 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 populate a document plan tree with the new message associated with the updateable data element at a predetermined location within the document plan tree.

20. A computer program product configured to transform one or more input data streams that comprise data that is at least partially expressed in a non-linguistic format into a format that can be expressed linguistically in one or more output texts, the computer program product comprising:

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

generate, via a natural language generation system that is configured to execute on a processor, a first output text based on a set of messages and a relationship between the set of messages, wherein a message represents a phrase or a simple sentence, and is created in an instance in which a first input data stream comprises data that satisfies one or more message requirements;

detect an updateable data element within a second input data stream, the updateable data element associated with a message of the set of messages, and the second input data stream comprising raw input data that is at least partially expressed in a non-linguistic form;

generate a new message associated with the updateable data element based on a predetermined indication and the second input data stream;

determine a classification for the new message by comparing the new message to a corresponding message associated with the first output text; and

generate, using the natural language generation system, an updated output text, wherein the updated output text comprises one or more natural language sentences and further comprises at least a portion of the first output text and at least a portion of the new message.