Techniques for inserting diacritical marks to text input via a user device

• US 8,812,302 B2
• Filed: 08/02/2012
• Issued: 08/19/2014
• Est. Priority Date: 01/17/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Xiao, Xiangye, Zhang, Yuanbo, Khoi, Vincent Ngo Bao, Yang, Fan, Liao, Baohua, Feng, Hanping
• Primary Examiner(s): Opsasnick, Michael N
• Application Number:
  US13/565,056
• Publication Number:
  US 20130185054A1
• Time in Patent Office: 747 Days
• Field of Search: 704/9
• US Class Current: 704/9
• CPC Class Codes: G06F 3/018 Input/output arrangements for oriental characters
• CPC Class Codes: G06F 40/109 Font handling; Temporal or kinetic typography
• CPC Class Codes: G06F 40/129 Handling non-Latin characters, e.g. kana-to-kanji conversion
• CPC Class Codes: G06F 40/274 Converting codes to words; Guess-ahead of partial word inputs

Abstract

A computer-implemented method for assisting a user to input Vietnamese text to a user device lacking a subset of characters in a Vietnamese alphabet includes receiving a character input by a user, determining three words previously input by the user, the three words having already had diacritical marks inserted, transmitting the three words and the character to a server via a network, receiving first and second information corresponding to the character from the server via the network, the first and second information generated at the server based on a context of the three words, the context determined at the server using a language model, the first and second information indicating whether the character requires a diacritical mark and a specific diacritical mark, respectively, generating a modified character comprising a character in the Vietnamese alphabet based on the character and the first and second information, and displaying the modified character.

Claims

1. A computer-implemented method for assisting a user to input Vietnamese text via a user interface of a user device lacking a subset of characters in a Vietnamese alphabet, the method comprising:

receiving, at the user device including the user interface, a display, and a processor, a character input by a user;

determining, at the user device, three words previously input by the user, the three words having already had diacritical marks inserted;

transmitting, from the user device, the three words and the character to a server via a network;

receiving, at the user device, at least one of first and second information corresponding to the character from the server via the network, the first and second information generated at the server based on a context of the three words, the context determined at the server using a language model, the first information indicating whether the character requires a diacritical mark, and the second information indicating a specific diacritical mark;

generating, at the user device, a modified character based on the character and the first and second information, the modified character comprising a character in the Vietnamese alphabet; and

displaying, via the display of the user device, the modified character.

2. A computer-implemented method, comprising:

receiving, at a user device including a user interface, a display, and a processor, a first character input by a user;

determining, at the user device, one or more second characters previously input by the user to the user device;

determining, at the user device, a context of the one or more second characters using a language model;

determining, at the user device, first information corresponding to the first character based on the context of the one or more second characters, the first information indicating whether the first character requires a diacritical mark;

when the first character requires a diacritical mark, determining, at the user device, second information corresponding to the first character based on the context of the one or more second characters, the second information indicating a specific diacritical mark;

generating, at the user device, a modified first character based on the first character and the first and second information; and

displaying, via the display of the user device, the modified first character.

3. The computer-implemented method of claim 2, wherein the language model is stored in the user device.

4. The computer-implemented method of claim 3, wherein the one or more second characters previously input by the user to the user device include two words.

5. The computer-implemented method of claim 2, further comprising transmitting, from the user device, the first character and the one or more second characters to a server via a network.

6. The computer-implemented method of claim 5, wherein the one or more second characters previously input by the user to the user device include three words.

7. The computer-implemented method of claim 6, wherein determining the context of the one or more second characters further comprises generating a score for each possible diacritical mark for the first character at the server based on the context, wherein each score indicates a likelihood that the first character requires one of the possible diacritical marks.

8. The computer-implemented method of claim 7, wherein determining the first and second information corresponding to the first character further comprises receiving, at the user device, the first and second information from the server, the first and second information being generated based on the scores and a predetermined threshold.

9. The computer-implemented method of claim 8, wherein the first information indicates that the first character requires a diacritical mark when one or more of the possible diacritical marks has a corresponding score greater than the predetermined threshold.

10. The computer-implemented method of claim 9, wherein when more than one of the possible diacritical marks has a corresponding score greater than the predetermined threshold, the second information indicates the diacritical mark having a highest corresponding score.

11. The computer-implemented method of claim 10, wherein generating the modified first character includes inserting the specific diacritical mark to the first character according to the first and second information.

12. A system, comprising:

an input determination module that determines a first character input by a user to a user device including a user interface, a display, and a processor, and that determines one or more second characters previously input by the user to the user device;

a context determination module that determines a context of the one or more second characters using a language model;

an information determination module that determines first information corresponding to the first character based on the context, the first information indicating whether the first character requires a diacritical mark, and that determines second information corresponding to the first character based on the context, the second information indicating a specific diacritical mark;

a mark insertion module that generates a modified first character based on the first character and the first and second information, wherein the modified first character comprises a character of a Vietnamese alphabet; and

an input control module that provides the modified first character to the user via the display of the user device.

13. The system of claim 12, wherein the language model is stored in the user device.

14. The system of claim 13, wherein the one or more second characters previously input by the user to the user device include two words.

15. The system of claim 12, further comprising a communication module that transmits the first character and the one or more second characters from the user device to a server via a network, and that receives the first and second information corresponding to the first character from the server via the network.

16. The system of claim 15, wherein the one or more second characters previously input by the user to the user device include three words.

17. The system of claim 16, wherein the server generates a score for each possible diacritical mark for the first character based on the context, wherein each score indicates a likelihood that the first character requires one of the possible diacritical marks.

18. The system of claim 17, wherein the server generates the first and second information based on the scores and a predetermined threshold, wherein the first information indicates that the first character requires a diacritical mark when one or more of the possible diacritical marks has a corresponding score greater than the predetermined threshold.

19. The system of claim 18, wherein when more than one of the possible diacritical marks has a corresponding score greater than the predetermined threshold, the second information indicates the diacritical mark having a highest corresponding score.

20. The system of claim 19, the mark insertion module generates the modified first character by inserting the specific diacritical mark to the first character according to the first and second information.