SERVER-BASED SPELL CHECKING

• US 20130060560A1
• Filed: 09/01/2011
• Published: 03/07/2013
• Est. Priority Date: 09/01/2011
• Status: Abandoned Application

• Current Assignee: Google Inc. (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Mahkovec, Ziga, Upson, Linus M., Bono, Hironori, Lim, Yew Jin
• Application Number:
  US13/224,159
• Publication Number:
  US 20130060560A1
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G06F 40/232 Orthographic correction, e.g. spell checking or vowelisation

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for server-based spell check. One aspect of the subject matter described in this specification can be embodied in methods performed by a server. The methods include the actions of receiving a request to spell check text; dividing the text into multiple segments, each segment including no more than a predetermined number of terms; providing each segment to a spell checker programmed to spell check an input including no more than the predetermined number of terms; receiving, from the spell checker, one or more spelling correction suggestions, each spelling correction suggestion corresponding to a term in a segment, the term being designated as misspelled by the spell checker; and assembling the received one or more spelling correction suggestions into a response to the request to spell check the text.

Claims

1. A method performed by data processing apparatus, the method comprising:

receiving a request to spell check text;

dividing the text into multiple segments, each segment comprising no more than a predetermined number of terms;

providing each segment to a spell checker programmed to spell check an input comprising no more than the predetermined number of terms;

receiving, from the spell checker, one or more spelling correction suggestions, each spelling correction suggestion corresponding to a term in a segment, the term being designated as misspelled by the spell checker; and

assembling the received one or more spelling correction suggestions into a response to the request to spell check the text.

2. The method of claim 1, wherein:

receiving the request, dividing the text, providing the segments to the spell checker, receiving the one or more spelling correction suggestions, and assembling the spelling correction suggestions are performed by a server,

receiving the request comprises receiving the request on the server through a data communication network from a user device, and

the method further comprises sending the response to the user device.

3. The method of claim 1, wherein dividing the text into multiple segments comprises:

dividing the text into one or more sentences; and

dividing each sentence into one or more segments.

4. The method of claim 1, wherein:

the text comprises a first term in a first language and a second term in a second language,

receiving the one or more spelling correction suggestions comprises;

receiving a first spelling correction suggestion for the first term, the first spelling correction suggestion being in the first language; and

receiving a second spelling correction suggestion for the second term, the second spelling correction suggestion being in the second language, and

the response to the request to spell correct the text comprises the first spelling correction suggestion in the first language and the second spelling correction suggestion being in the second language.

5. The method of claim 1, comprising:

generating a language model from a collection of documents; and

configuring the spell checker using the language model.

6. The method of claim 5, wherein generating the language model from a collection of documents comprises generating a generic language model and generating an overlay language model, the overlay language model being specific to a user.

7. The method of claim 1, comprising:

generating a noisy channel model from a collection of documents; and

configuring the spell checker using the noisy channel model.

8. The method of claim 1, wherein assembling the received one or more spelling correction suggestions comprises truecasing the one or more spelling correction suggestions based on a truecasing language model.

9. The method of claim 1, further comprising:

receiving, from the spell checker, a dirty word indicator indicating the term includes a word that is pornographic, obscene, or offensive, wherein assembling the received one or more spelling correction suggestions into a response comprises associating the dirty word indicator with the term in the response.

10. A computer program product configured to cause data processing apparatus to perform operations comprising:

receiving a request to spell check text;

dividing the text into multiple segments, each segment comprising no more than a predetermined number of terms;

providing each segment to a spell checker programmed to spell check an input comprising no more than the predetermined number of terms;

receiving, from the spell checker, one or more spelling correction suggestions, each spelling correction suggestion corresponding to a term in a segment, the term being designated as misspelled by the spell checker; and

assembling the received one or more spelling correction suggestions into a response to the request to spell check the text.

11. The product of claim 10, wherein:

receiving the request, dividing the text, providing the segments to the spell checker, receiving the one or more spelling correction suggestions, and assembling the spelling correction suggestions are performed by a server,

receiving the request comprises receiving the request on the server through a data communication network from a user device, and

the operation further comprise sending the response to the user device.

12. The product of claim 10, wherein dividing the text into multiple segments comprises:

dividing the text into one or more sentences; and

dividing each sentence into one or more segments.

13. The product of claim 10, wherein:

the text comprises a first term in a first language and a second term in a second language,

receiving the one or more spelling correction suggestions comprises;

receiving a first spelling correction suggestion for the first term, the first spelling correction suggestion being in the first language; and

receiving a second spelling correction suggestion for the second term, the second spelling correction suggestion being in the second language, and

the response to the request to spell correct the text comprises the first spelling correction suggestion in the first language and the second spelling correction suggestion being in the second language.

14. The product of claim 10, the operations comprising:

generating a language model from a collection of documents; and

configuring the spell checker using the language model.

15. The product of claim 14, wherein generating the language model from a collection of documents comprises generating a generic language model and generating an overlay language model, the overlay language model being specific to a user.

16. The product of claim 10, the operations comprising:

generating a noisy channel model from a collection of documents; and

configuring the spell checker using the noisy channel model.

17. The product of claim 10, wherein assembling the received one or more spelling correction suggestions comprises truecasing the one or more spelling correction suggestions based on a truecasing language model.

18. The product of claim 10, the operations further comprising:

receiving, from the spell checker, a dirty word indicator indicating the term includes a word that is pornographic, obscene, or offensive, wherein assembling the received one or more spelling correction suggestions into a response comprises associating the dirty word indicator with the term in the response.

19. A system comprising:

one or more computers configured to perform operations comprising;

receiving a request to spell check text;

dividing the text into multiple segments, each segment comprising no more than a predetermined number of terms;

providing each segment to a spell checker programmed to spell check an input comprising no more than the predetermined number of terms;

receiving, from the spell checker, one or more spelling correction suggestions, each spelling correction suggestion corresponding to a term in a segment, the term being designated as misspelled by the spell checker; and

assembling the received one or more spelling correction suggestions into a response to the request to spell check the text.

20. The system of claim 19, wherein:

receiving the request, dividing the text, providing the segments to the spell checker, receiving the one or more spelling correction suggestions, and assembling the spelling correction suggestions are performed by a server,

receiving the request comprises receiving the request on the server through a data communication network from a user device, and

the operations further comprise sending the response to the user device.

21. The system of claim 19, wherein dividing the text into multiple segments comprises:

dividing the text into one or more sentences; and

dividing each sentence into one or more segments.

22. The system of claim 19, wherein:

the text comprises a first term in a first language and a second term in a second language,

receiving the one or more spelling correction suggestions comprises;

receiving a first spelling correction suggestion for the first term, the first spelling correction suggestion being in the first language; and

receiving a second spelling correction suggestion for the second term, the second spelling correction suggestion being in the second language, and

the response to the request to spell correct the text comprises the first spelling correction suggestion in the first language and the second spelling correction suggestion being in the second language.

23. The system of claim 19, the operations comprising:

generating a language model from a collection of documents; and

configuring the spell checker using the language model.

24. The system of claim 23, wherein generating the language model from a collection of documents comprises generating a generic language model and generating an overlay language model, the overlay language model being specific to a user.

25. The system of claim 19, the operations comprising:

generating a noisy channel model from a collection of documents; and

configuring the spell checker using the noisy channel model.

26. The system of claim 19, wherein assembling the received one or more spelling correction suggestions comprises truecasing the one or more spelling correction suggestions based on a truecasing language model.

27. The system of claim 19, the operations further comprising:

receiving, from the spell checker, a dirty word indicator indicating the term includes a word that is pornographic, obscene, or offensive, wherein assembling the received one or more spelling correction suggestions into a response comprises associating the dirty word indicator with the term in the response.