Systems and methods for determining relevant information based on document structure

• US 20070143098A1
• Filed: 12/12/2005
• Published: 06/21/2007
• Est. Priority Date: 12/12/2005
• Status: Active Grant

• Current Assignee: Fuji Xerox Company Limited (Xerox Holdings Corp.)
• Original Assignee: Fuji Xerox Company Limited (Xerox Holdings Corp.)
• Inventors: Chiu, Patrick, Liew, Bee, Polanyi, Livia, Rieffel, Eleanor, Van Den Berg, Martin, Thione, Giovanni
• Granted Patent: US 7,739,279 B2
• Time in Patent Office: Days
• US Class Current: 704/1
• CPC Class Codes: G06F 40/35 Discourse or dialogue representation

Abstract

Techniques are provided for determining relevant information from a document based on document structure. A document is selected and structural elements within the document having a dominance relationship are determined. A first location within the document is selected. The structural element surrounding the first location is determined and the surrounding and non-surrounding structural elements are characterized. Additional documents are associated with the first location in the surrounding structural element based on the surrounding structural element characterization and the non-surrounding structural element characterization. Techniques for dynamically determining annotations for images based on document structure are also provided.

Claims

1. A method of determining information relevant to a paragraph comprising the steps of:

determining a document;

identifying at least two structural elements in the document having a dominance relationship;

selecting a first location in the document;

determining the structural element surrounding the first location;

characterizing the surrounding structural element;

characterizing the non-surrounding structural elements; and

associating at least one additional document with the surrounding structural element based on the characterization of the surrounding and non-surrounding structural elements.

2. The method of claim 1, in which the structural elements are determined based on explicit or implicit information.

3. The method of claim 2, in which the implicit information is determined based on a theory of analysis.

4. The method of claim 3, in which the theory of analysis is at least one of:

the Linguistic Discourse Model (LDM), the Universal Linguistic Discourse Model (ULDM), the Discourse Structures Theory (DST), the Rhetorical Structures Theory (RST), and Structure Discourse Representation Theory (SDRT).

5. The method of claim 1, in which the first location is selected based on at least one of:

manually and programmatic control.

6. The method of claim 5, in which the manual selection of the first location is based on at least one of:

implicit and explicit user input.

7. The method of claim 1, in which characterizing the structural elements is based on at least one of:

latent semantic analysis and similarity of representative vectors.

8. The method of claim 1, in which the at least one additional document is based on a similarity characterization of the surrounding structural element and a dissimilarity characterization of the non-surrounding structural element.

9. The method of claim 1, in which additional documents comprise human sensible information.

10. The method of claim 9, in which the human sensible information is at least one of textual, audio and video information.

11. The method of claim 1, in which the determined document comprises at least one of textual, audio and video information.

12. An apparatus for determining relevant information comprising:

an input/output circuit that retrieves a document from a document repository;

a document structure manager that identifies at least two structural elements in the retrieved document having a dominance relationship;

a structural element manager that identifies the structural element surrounding a selected first location and the non-surrounding structural elements;

a characterization manager that characterizes the surrounding and non-surrounding structural elements;

a search manager that selectively associates additional documents with the first location in the retrieved document based on the characterizations of the surrounding and non-surrounding structural elements.

13. The apparatus of claim 12, in which the structural element manager determines structural elements based on explicit or implicit information.

14. The apparatus of claim 13, in which the implicit information is determined based on theory of analysis.

15. The apparatus of claim 14, in which the theory of analysis is at least one of:

the Linguistic Discourse Model (LDM), the Universal Linguistic Discourse Model (ULDM), the Discourse Structures Theory (DST), the Rhetorical Structures Theory (RST), and Structure Discourse Representation Theory (SDRT).

16. The apparatus of claim 12, in which the first location is selected based on at least one of:

manually and programmatically.

17. The apparatus of claim 15, in which the manual selection of the first location is based on at least one of:

implicit and explicit user input.

18. The apparatus of claim 12, in which characterizing the structural elements is based on at least one of:

latent semantic analysis, and similarity of representative vectors.

19. The apparatus of claim 12, in which the at least one additional document is based on a similarity characterization of the surrounding structural element and a dissimilarity characterization of the non-surrounding structural element.

20. The apparatus of claim 12, in which additional documents comprise human sensible information.

21. The apparatus of claim 20, in which the human sensible information is at least one of textual, audio and video information.

22. The apparatus of claim 12, in which the determined document comprises at least one of textual, audio and video information.

23. A computer readable storage medium comprising computer readable program code embodied on the computer readable storage medium, the computer readable program code useable to program a computer for determining relevant information comprising the steps of:

determining a document;

identifying at least two structural elements in the document having a dominance relationship;

selecting a first location in the document;

determining the structural element surrounding the first location;

characterizing the surrounding structural element;

characterizing the non-surrounding structural elements; and

associating at least one additional document with the surrounding structural element based on the characterization of the surrounding and non-surrounding structural elements.