Techniques for automatic proofing of textual data

• US 10,691,887 B2
• Filed: 06/01/2018
• Issued: 06/23/2020
• Est. Priority Date: 04/09/2018
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Powell, Kevin R., Cipollone, Domenic J., Daniels, Michael W., Gauthier, Olivier M.
• Primary Examiner(s): He, Jialong
• Application Number:
  US15/995,699
• Publication Number:
  US 20190311031A1
• Time in Patent Office: 753 Days
• CPC Class Codes: G06F 40/166 Editing, e.g. inserting or deleting
• CPC Class Codes: G06F 40/216 using statistical methods
• CPC Class Codes: G06F 40/232 Orthographic correction, e.g. spell checking or vowelisation
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique

Abstract

Techniques for automatic proofing of textual data is described. In one embodiment, these techniques are directed towards producing proofed textual data for various operational environments via logic operative on a logic circuit to access information comprising a set of n-grams, at least one mapping between at least one replacement n-gram and a corresponding n-gram in the set of n-grams, and a corresponding confidence score for each mapping being determined by user activity while producing text for various applications; process input to a productivity application comprising textual data and identify a portion thereof to replace based upon the accessed information; and automatically modify the portion of the textual data using a replacement n-gram selected from the replacement n-grams based upon a corresponding confidence score between the portion of the textual data and the replacement n-gram. Other embodiments are described and claimed.

Claims

1. An apparatus, comprising:

a logic circuit; and

logic operative on the logic circuit to access information comprising;

a set of n-grams, each n-gram in the set comprising a plurality of words,

a set of replacement n-grams, each replacement n-gram having a same number of words as the plurality of words,

at least one mapping between at least one replacement n-gram for a corresponding n-gram in the set of n-grams, and

a corresponding confidence score for each mapping being determined by user activity while producing text for various one or more applications, wherein a higher confidence score for a mapping for an n-gram corresponds to a higher number of users replacing the n-gram with a first replacement n-gram, and a lower confidence score for the mapping corresponds to a lower number of users replacing the n-gram with a second replacement n-gram;

the logic further operative on the logic circuit to;

process input to a productivity application comprising textual data;

identify a portion of the textual data to replace based upon the accessed information; and

automatically modify the portion of the textual data using at least one word from the replacement n-grams based upon a corresponding confidence score between the portion of the textual data and the at least one word.

2. The apparatus of claim 1 further comprising logic operative on the logic circuit to identify an error in the portion of the textual data.

3. The apparatus of claim 2 wherein the error comprises at least one of a spelling error, a grammatical error, or a style error.

4. The apparatus of claim 1 further comprising logic operative on the logic circuit to replace a word in the portion of the textual data with a word from the replacement n-grams.

5. The apparatus of claim 1 further comprising logic operative on the logic circuit to generate a mapping between an n-gram in the set of n-grams and a replacement n-gram in response to a user selection, amongst a number of n-grams, of the replacement n-gram for the n-gram in the set of n-grams, and compute the corresponding confidence score for the mapping based upon telemetry data associated with the various applications.

6. The apparatus of claim 1 further comprising logic operative on the logic circuit to identify a word having an error in the textual data and modifying the word to correct the error if the error exceeds an autocorrection threshold value.

7. The apparatus of claim 6 further comprising logic operative on the logic circuit to modify the autocorrection threshold value in view of telemetry data corresponding to the user activity.

8. A computer-implemented method, comprising:

accessing information comprising;

a set of n-grams, each n-gram in the set comprising a plurality of words,

a set of replacement n-grams, each replacement n-gram having a same number of words as the plurality of words,

at least one mapping between at least one replacement n-gram and an n-gram in the set of n-grams, and

a corresponding confidence score for each mapping being determined by user activity while producing text for one or more computing applications, wherein a higher confidence score for a mapping for an n-gram corresponds to a higher number of users replacing the n-gram with a first replacement n-gram, and a lower confidence score for the mapping corresponds to a lower number of users replacing the n-gram with a second replacement n-gram;

processing input to a productivity application comprising textual data;

identifying a portion of the textual data to replace based upon the accessed information; and

automatically modifying the portion of the textual data using a replacement n-gram selected from the replacement n-grams based upon a corresponding confidence score between the portion of the textual data and the replacement n-gram.

9. The method of claim 8 further comprising identifying an error in the portion of the textual data.

10. The method of claim 9, wherein the error comprises at least one of a spelling error, a grammatical error, or a style error.

11. The method of claim 8 further comprising replacing a word in the portion of the textual data with a word from the replacement n-grams.

12. The method of claim 8 further comprising generating a mapping between an n-gram in the set of n-grams and the replacement n-gram in response to a user selection, amongst a number of n-grams, of the replacement n-gram for the n-gram in the set of n-grams, and computing the corresponding confidence score for the mapping based upon telemetry data associated with the various applications.

13. The method of claim 8 further comprising identifying a word having an error in the textual data and modifying the word to correct the error if the error exceeds an autocorrection threshold value.

14. The method of claim 13 further comprising modifying the autocorrection threshold value in view of telemetry data associated with the various computing applications.

15. At least one computer-readable storage device comprising instructions that, when executed, cause a system to:

access information comprising;

a set of n-grams, each n-gram in the set comprising a plurality of words,

a set replacement n-grams, each replacement n-gram having a same number of words as the plurality of words,

at least one mapping between at least one replacement n-gram and a corresponding n-gram in the set of n-grams, and

a corresponding confidence score for each mapping being determined by user activity while producing text for one or more applications, wherein a higher confidence score for a mapping for an n-gram corresponds to a higher number of users replacing the n-gram with a first replacement n-gram, and a lower confidence score for the mapping corresponds to a lower number of users replacing the n-gram with a second replacement n-gram;

process input to a productivity application comprising textual data;

identify a portion of the textual data to replace based upon the accessed information; and

automatically modify the portion of the textual data using a replacement n-gram selected from the replacement n-grams based upon a corresponding confidence score between the portion of the textual data and the replacement n-gram.

16. The computer-readable storage device of claim 15, comprising instructions that when executed cause the system to:

identify an error in the portion of the textual data, wherein the error comprises at least one of a spelling error, a grammatical error, or a style error.

17. The computer-readable storage device of claim 15, comprising instructions that when executed cause the system to:

replace a word in the portion of the textual data with a word from the replacement n-grams.

18. The computer-readable storage device of claim 15, comprising instructions that when executed cause the system to:

generate a mapping between an n-gram in the set of n-grams and a replacement n-gram in response to a user selection, amongst a number of n-grams, of the replacement n-gram for the n-gram in the set of n-grams; and

compute the corresponding confidence score for the mapping based upon telemetry data associated with the various applications.

19. The computer-readable storage device of claim 15, comprising instructions that when executed cause the system to:

identify a word having an error in the textual data and modifying the word to correct the error if the error exceeds an autocorrection threshold value.

20. The computer-readable storage device of claim 19, comprising instructions that when executed cause the system to:

modify the autocorrection threshold value in view of telemetry data corresponding to the user activity.