Information extraction combining spatial and textual layout cues

1. A method for extracting information from a formatted document, wherein the method comprises:

combining one or more visual layout rules, one or more mark-up rules and one or more text-based rules for information extraction from a formatted document, wherein combining one or more visual layout rules, one or more mark-up rules and one or more text-based rules comprises:

extracting all visual regions of one or more formatted documents;

providing one or more annotations pertaining to the extracted visual regions to a spatial database; and

creating one or more indexes on the extracted visual regions to facilitate evaluation of one or more visual layout rules; and

specifying one or more rules from the one or more visual layout rules, one or more mark-up rules and one or more text based rules to extract information from the formatted document and converting the one or more rules into one or more queries that can be understood by the spatial database.

2. The method of claim 1 , wherein the one or more visual layout rules comprise specification of a direction of a region with respect to another region.

3. The method of claim 1 , wherein the one or more visual layout rules comprise an area of a region.

4. The method of claim 1 , wherein the one or more visual layout rules comprise a location of a region within one or more additional regions.

5. The method of claim 1 , wherein the one or more visual layout rules comprise an alignment of a set of one or more regions.

6. The method of claim 1 , wherein the one or more visual layout rules comprise a distance between two or more regions.

7. The method of claim 1 , wherein the one or more visual layout rules comprise a property of a region.

8. The method of claim 1 , wherein the one or more visual layout rules comprise an aggregation operator.

9. The method of claim 1 , further comprising storing one or more annotations with an associated visual region.

10. The method of claim 1 , further comprising formatting information extracted from a formatted document in a database.

11. The method of claim 1 , further comprising indexing each region extracted from a formatted document using a spatial database.

12. The method of claim 1 , further comprising indexing each region extracted from a formatted document using a custom index structure.

13. The method of claim 1 , further comprising using a text index in combination with a spatial index for efficient implementation of one or more rules combining text and spatial layout-based rules.

14. The method of claim 1 , further comprising providing a system, wherein the system comprises one or more distinct software modules, each of the one or more distinct software modules being embodied on a tangible computer-readable recordable storage medium, and wherein the one or more distinct software modules comprise a visual region extractor module, a spatial database module, a spatial indexer module and a rules engine module executing on a hardware processor.

15. A computer program product comprising a tangible computer readable recordable storage medium including computer useable program code for extracting information from a formatted document, the computer program product including:

computer useable program code for combining one or more visual layout rules, one or more mark-up rules and one or more text-based rules for information extraction from a formatted document, wherein computer useable program code for combining one or more visual layout rules, one or more mark-up rules and one or more text-based rules comprises:

computer useable program code for extracting all visual regions of one or more formatted documents;

computer useable program code for providing one or more annotations pertaining to the extracted visual regions to a spatial database; and

computer useable program code for creating one or more indexes on the extracted visual regions to facilitate evaluation of one or more visual layout rules; and

computer useable program code for specifying one or more rules from the one or more visual layout rules, one or more mark-up rules and one or more text based rules to extract information from the formatted document and converting the one or more rules into one or more queries that can be understood by the spatial database.

16. The computer program product of claim 15 , wherein the one or more visual layout rules comprise an aggregation operator.

17. The computer program product of claim 15 , wherein the one or more visual layout rules comprise at least one of specification of a direction of a region with respect to another region, an area of a region, a location of a region within one or more additional regions, an alignment of a set of one or more regions, a distance between two or more regions and a property of a region.

18. The computer program product of claim 15 , further comprising computer useable program code for using a text index in combination with a spatial index for efficient implementation of one or more rules combining text and spatial layout-based rules.

19. The computer program product of claim 15 , wherein the computer useable program code comprises one or more distinct software modules, and wherein the one or more distinct software modules comprise a visual region extractor module, a spatial database module, a spatial indexer module and a rules engine module executing on a hardware processor.

20. A system for extracting information from a formatted document, comprising:

a memory; and at least one processor coupled to the memory and operative to:

combine one or more visual layout rules, one or more mark-up rules and one or more text-based rules for information extraction from a formatted document, wherein combining one or more visual layout rules, one or more mark-up rules and one or more text-based rules comprises:

extracting all visual regions of one or more formatted documents;

providing one or more annotations pertaining to the extracted visual regions to a spatial database; and

creating one or more indexes on the extracted visual regions to facilitate evaluation of one or more visual layout rules; and

specify one or more rules from the one or more visual layout rules, one or more mark-up rules and one or more text based rules to extract information from the formatted document and convert the one or more rules into one or more queries that can be understood by the spatial database.

21. The system of claim 20 , wherein the one or more visual layout rules comprise an aggregation operator.

22. The system of claim 20 , wherein the one or more visual layout rules comprise at least one of specification of a direction of a region with respect to another region, an area of a region, a location of a region within one or more additional regions, an alignment of a set of one or more regions, a distance between two or more regions and a property of a region.

23. The system of claim 20 , wherein the at least one processor coupled to the memory is further operative to use a text index in combination with a spatial index for efficient implementation of one or more rules combining text and spatial layout-based rules.

24. The system of claim 20 , further comprising a tangible computer-readable recordable storage medium having one or more distinct software modules embodied thereon, the one or more distinct software modules comprising a visual region extractor module, a spatial database module, a spatial indexer module and a rules engine module executing on a hardware processor.

25. An apparatus for extracting information from a formatted document, the apparatus comprising:

means for combining one or more visual layout rules, one or more mark\-up rules and one or more text-based rules for information extraction from a formatted document, wherein means for combining one or more visual layout rules, one or more mark-up rules and one or more text-based rules comprises:

means for extracting all visual regions of one or more formatted documents;

means for providing one or more annotations pertaining to the extracted visual regions to a spatial database; and

means for creating one or more indexes on the extracted visual regions to facilitate evaluation of one or more visual layout rules; and

means for specifying one or more rules from the one or more visual layout rules, one or more mark-up rules and one or more text based rules to extract information from the formatted document and converting the one or more rules into one or more queries that can be understood by the spatial database.