PREDICTIVE CONVERSION OF LANGUAGE INPUT

• US 20150370780A1
• Filed: 08/28/2015
• Published: 12/24/2015
• Est. Priority Date: 05/30/2014
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: WANG, Xin, RAMERTH, Brent D.
• Granted Patent: US 9,842,101 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/3322 using system suggestions G06F16/3325 takes precedence
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 3/018 Input/output arrangements for oriental characters
• 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

Systems and processes for predictive conversion of language input are provided. In one example process, text composed by a user can be obtained. Input comprising a sequence of symbols of a first symbolic system can be received from the user. Candidate word strings corresponding to the sequence of symbols can be determined. Each candidate word string can comprise two or more words of a second symbolic system. The candidate word strings can be ranked based on a probability of occurrence of each candidate word string in the obtained text. Based on the ranking, a portion of the candidate word strings can be displayed for selection by the user.

Claims

1. A method for converting language input, the method comprising:

at an electronic device having one or more processors and memory;

obtaining text composed by a user;

receiving, from the user, input comprising a sequence of symbols of a first symbolic system;

determining a plurality of candidate word strings corresponding to the sequence of symbols, each candidate word string of the plurality of candidate word strings comprising two or more words of a second symbolic system;

ranking the plurality of candidate word strings based on a probability of occurrence of each candidate word string of the plurality of candidate word strings in the obtained text; and

displaying, based on the ranking, a portion of the plurality of candidate word strings for selection by the user.

2. The method of claim 1, wherein the first symbolic system is different from the second symbolic system.

3. The method of claim 1, further comprising:

generating a first language model using the obtained text; and

determining, using the first language model, the probability of occurrence of each candidate word string of the plurality of candidate word strings in the obtained text.

4. The method of claim 3, wherein the first language model is an n-gram language model.

5. The method of claim 3, further comprising:

receiving, from the user, a selection of a candidate word string from the displayed portion of the plurality of candidate word strings; and

displaying the selected candidate word string in a text field of the electronic device.

6. The method of claim 5, further comprising:

receiving an indication that the user has committed to the selected candidate word string; and

in response to receiving the indication, updating the first language model using the selected candidate word string.

7. The method of claim 6, wherein receiving the indication further comprises receiving a full stop input for a sentence containing the selected candidate word string.

8. The method of claim 6, wherein receiving the indication further comprises receiving a command to send a message containing the selected candidate word string.

9. The method of claim 5, further comprising:

determining a predicted word of the second symbolic system based on a probability of occurrence of a sequence of words in the obtained text, the sequence of words comprising the selected candidate word string and the predicted text; and

displaying the predicted word adjacent to the selected candidate word string in the text field.

10. The method of claim 1, wherein:

the obtained text is associated with a first context;

the input is associated with an input context; and

ranking the plurality of candidate word strings is based on a degree of similarity between the input context and the first context.

11. The method of claim 10, wherein the first context includes a first recipient and a first application of the electronic device, and wherein the input context includes a second recipient and a second application of the electronic device.

12. The method of claim 10, wherein the first context and input context are determined using a sensor of the electronic device.

13. The method of claim 1, further comprising:

obtaining second text composed by the user, wherein;

the obtained second text is associated with a second context;

ranking the plurality of candidate word strings is based on a probability of occurrence of each candidate word string of the plurality of candidate word strings in the second obtained text; and

the ranking the plurality of candidate word strings is based on a degree of similarity between the input context and the second context.

14. The method of claim 13, wherein the obtained second text comprises words of the second symbolic system.

15. The method of claim 1, wherein the obtained text comprises words of the second symbolic system.

16. The method of claim 1, further comprising:

determining, using a second language model, a probability of occurrence of each candidate word string of the plurality of candidate word strings in a corpus of text, wherein ranking the plurality of candidate word strings is based on the probability of occurrence of each candidate word string of the plurality of candidate word strings in the corpus of text, and wherein the corpus of text is not composed by the user.

17. The method of claim 1, wherein the first symbolic system comprises a phonetic system for transcribing a language.

18. The method of claim 1, wherein the first symbolic system comprises Chinese Pinyin.

19. The method of claim 1, wherein the first symbolic system comprises Chinese Zhuyin.

20. The method of claim 1, wherein the second symbolic system comprises Chinese characters.

21. The method of claim 1, wherein each word of the two or more words is a monosyllabic Chinese character.

22. A non-transitory computer-readable storage medium comprising computer-executable instructions, which when executed by one or more processors, causes the one or more processors to:

obtain text composed by a user;

receive, from the user, input comprising a sequence of symbols of a first symbolic system;

determine a plurality of candidate word strings corresponding to the sequence of symbols, each candidate word string of the plurality of candidate word strings comprising two or more words of a second symbolic system;

rank the plurality of candidate word strings based on a probability of occurrence of each candidate word string of the plurality of candidate word strings in the obtained text; and

display, based on the ranking, a portion of the plurality of candidate word strings for selection by the user.

23. A system comprising:

one or more processors;

memory storing computer-readable instructions, which when executed by the one or more processors, cause the one or more processors to;

obtain text composed by a user;

receive, from the user, input comprising a sequence of symbols of a first symbolic system;

determine a plurality of candidate word strings corresponding to the sequence of symbols, each candidate word string of the plurality of candidate word strings comprising two or more words of a second symbolic system;

rank the plurality of candidate word strings based on a probability of occurrence of each candidate word string of the plurality of candidate word strings in the obtained text; and

display, based on the ranking, a portion of the plurality of candidate word strings for selection by the user.

24. The system of claim 23, wherein the computer-readable instructions further cause the one or more processors to:

generate a first language model using the obtained text; and

determine, using the first language model, the probability of occurrence of each candidate word string of the plurality of candidate word strings in the obtained text.

25. The system of claim 24, wherein the computer-readable instructions further cause the one or more processors to:

receive, from the user, a selection of a candidate word string from the displayed portion of the plurality of candidate word strings; and

display the selected candidate word string in a text field.