Text segmentation and label assignment with user interaction by means of topic specific language models and topic-specific label statistics

• US 8,688,448 B2
• Filed: 09/14/2012
• Issued: 04/01/2014
• Est. Priority Date: 11/21/2003
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Nuance Communications Austria Gmbh (Microsoft Corporation)
• Inventors: Peters, Jochen, Matusov, Evgeny, Meyer, Carsten, Klakow, Dietrich
• Primary Examiner(s): Opsasnick, Michael N
• Application Number:
  US13/619,972
• Publication Number:
  US 20130066625A1
• Time in Patent Office: 564 Days
• Field of Search: 704/236, 704/9, 704/10
• US Class Current: 704/236
• CPC Class Codes: G06F 40/10 Text processing natural language analysis G06F40/20; semantic analysis G06F40/30; processing or translation of natural language G06F40/40
• CPC Class Codes: G06F 40/279 Recognition of textual entities
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

The invention relates to a method, a computer program product, a segmentation system and a user interface for structuring an unstructured text by making use of statistical models trained on annotated training data. The method performs text segmentation into text sections and assigns labels to text sections as section headings. The performed segmentation and assignment is provided to a user for general review. Additionally, alternative segmentations and label assignments are provided to the user being capable to select alternative segmentations and alternative labels as well as to enter a user defined segmentation and user defined label. In response to the modifications introduced by the user, a plurality of different actions are initiated incorporating the re-segmentation and re-labeling of successive parts of the document or the entire document.

Claims

1. A system comprising at least one processor programmed to:

segment an unstructured text into a plurality of text sections;

identify a portion of text that fully or partially identifies a section heading for a first text section of the plurality of text sections;

remove, from the first text section, the portion of text that fully or partially identifies the section heading;

create a structured text comprising the first text section and the section heading for the first text section, wherein the portion of text that fully or partially identifies the section heading has been removed from the first text section; and

provide the structured text to a user.

2. The system of claim 1, wherein the section heading is a first section heading, and wherein the at least one processor is further programmed to:

provide to the user a plurality of alternative section headings for the first text section.

3. The system of claim 2, wherein the structured text is a first structured text, and wherein the at least one processor is further programmed to:

receive user input indicative of the user selecting an alternative section heading from the plurality of alternative section headings to replace the first section heading; and

provide to the user a second structured text in which the first section heading has been replaced by the alternative section heading selected by the user.

4. The system of claim 1, wherein the at least one processor is further programmed to:

receive user input indicative of the user disapproving the section heading; and

in response to the user input, re-insert the portion of text that fully or partially identifies the section heading into the first text section.

5. The system of claim 1, wherein the at least one processor is further programmed to:

receive user input indicative of the user wishing to move a border between a second text section and a third text section from a first position in the structured text to a second position in the structured text; and

provide to the user a second structured text in which the border between the second text section and the third text section has been moved to the second position indicated by the user.

6. The system of claim 5, wherein the at least one processor is further programmed to:

re-segment the structured text while leaving the border between the second text section and the third text section at the second position indicated by the user.

7. The system of claim 1, wherein the at least one processor is further programmed to:

select the section heading based at least in part on a topic assigned to the first text section.

8. A method comprising acts of:

segmenting an unstructured text into a plurality of text sections;

using at least one processor to identify a portion of text that fully or partially identifies a section heading for a first text section of the plurality of text sections;

removing, from the first text section, the portion of text that fully or partially identifies the section heading;

creating a structured text comprising the first text section and the section heading for the first text section, wherein the portion of text that fully or partially identifies the section heading has been removed from the first text section; and

providing the structured text to a user.

9. The method of claim 8, wherein the section heading is a first section heading, and wherein the method further comprises:

providing to the user a plurality of alternative section headings for the first text section.

10. The method of claim 9, wherein the structured text is a first structured text, and wherein the method further comprises:

receiving user input indicative of the user selecting an alternative section heading from the plurality of alternative section headings to replace the first section heading; and

providing to the user a second structured text in which the first section heading has been replaced by the alternative section heading selected by the user.

11. The method of claim 8, further comprising:

receiving user input indicative of the user disapproving the section heading; and

in response to the user input, re-inserting the portion of text that fully or partially identifies the section heading into the first text section.

12. The method of claim 8, further comprising:

receiving user input indicative of the user wishing to move a border between a second text section and a third text section from a first position in the structured text to a second position in the structured text; and

providing to the user a second structured text in which the border between the second text section and the third text section has been moved to the second position indicated by the user.

13. The method of claim 12, further comprising:

re-segmenting the structured text while leaving the border between the second text section and the third text section at the second position indicated by the user.

14. The method of claim 8, further comprising:

selecting the section heading based at least in part on a topic assigned to the first text section.

15. At least one non-transitory computer-readable medium having stored thereon instructions that, when executed by at least one processor, perform a method comprising acts of:

segmenting an unstructured text into a plurality of text sections;

using at least one processor to identify a portion of text that fully or partially identifies a section heading for a first text section of the plurality of text sections;

removing, from the first text section, the portion of text that fully or partially identifies the section heading;

creating a structured text comprising the first text section and the section heading for the first text section, wherein the portion of text that fully or partially identifies the section heading has been removed from the first text section; and

providing the structured text to a user.

16. The at least one non-transitory computer-readable medium of claim 15, wherein the section heading is a first section heading, and wherein the method further comprises:

providing to the user a plurality of alternative section headings for the first text section.

17. The at least one non-transitory computer-readable medium of claim 16, wherein the structured text is a first structured text, and wherein the method further comprises:

receiving user input indicative of the user selecting an alternative section heading from the plurality of alternative section headings to replace the first section heading; and

providing to the user a second structured text in which the first section heading has been replaced by the alternative section heading selected by the user.

18. The at least one non-transitory computer-readable medium of claim 15, wherein the method further comprises:

receiving user input indicative of the user disapproving the section heading; and

in response to the user input, re-inserting the portion of text that fully or partially identifies the section heading into the first text section.

19. The at least one non-transitory computer-readable medium of claim 15, wherein the method further comprises:

receiving user input indicative of the user wishing to move a border between a second text section and a third text section from a first position in the structured text to a second position in the structured text; and

providing to the user a second structured text in which the border between the second text section and the third text section has been moved to the second position indicated by the user.

20. The at least one non-transitory computer-readable medium of claim 19, wherein the method further comprises:

re-segmenting the structured text while leaving the border between the second text section and the third text section at the second position indicated by the user.