Multilingual word prediction

1. An electronic device, comprising:

one or more processors;

a display;

a memory; and

one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for:

receiving context information associated with a current word, wherein the context information includes one or more words stored on the electronic device;

determining, for each of a plurality of languages, a set of monolingual probabilities based on the context information;

determining a set of language weights based on the context information;

determining a set of multilingual probabilities based on the respective sets of monolingual probabilities and the set of language weights; and

providing, on the display, a plurality of candidate words based on the set of multilingual probabilities.

2. The electronic device of claim 1 , wherein the context information includes a plurality of words, wherein determining a set of language weights comprises:

identifying a language of each word of the plurality of words.

3. The electronic device of claim 2 , wherein the one or more programs further include instructions for:

providing a language identification string indicative of the language of each word of the plurality of words.

4. The electronic device of claim 1 , wherein the current word is associated with a sentence and the context information is based on one or more words of the sentence.

5. The electronic device of claim 1 , wherein the one or more programs further include instructions for:

selecting a candidate word of the plurality of candidate words associated with a multilingual probability of the set of multi-lingual probabilities having a greatest magnitude.

6. The electronic device of claim 5 , wherein the one or more programs further include instructions for:

replacing an at least partial word input with the selected candidate word of the plurality of candidate words.

7. The electronic device of claim 1 , wherein the one or more programs further include instructions for:

providing, for each of the plurality of languages, a respective set of candidate words, wherein each set of candidate words corresponds to a respective language of the plurality of languages,

wherein providing a plurality of candidate words based on the set of multilingual probabilities comprises:

selecting the plurality of candidate words from one or more of the sets of candidate words based on the set of multilingual probabilities.

8. The electronic device of claim 1 , wherein determining, for each of a plurality of languages, a set of monolingual probabilities based on the context information comprises:

determining each set of monolingual probabilities using a respective monolingual language model.

9. The electronic device of claim 1 , wherein determining, for each of a plurality of languages, a set of monolingual probabilities based on the context information comprises:

determining each set of monolingual probabilities using text prediction.

10. The electronic device of claim 9 , wherein determining each set of monolingual probabilities using text prediction comprises:

determining each set of monolingual probabilities using a continuous-space language model.

11. The electronic device of claim 9 , wherein determining each set of monolingual probabilities using text prediction comprises:

determining each set of monolingual probabilities using an n-gram language model.

12. The electronic device of claim 1 , wherein the one or more programs further include instructions for:

adjusting at least one of the set of monolingual probabilities or the set of multilingual probabilities based on context information of the electronic device.

13. The electronic device of claim 12 , wherein the context information of the electronic device includes at least one word of a language of a keyboard enabled on the electronic device.

14. The electronic device of claim 12 , wherein the context information of the electronic device includes at least one word of a language used in a conversation between users of an application.

15. A non-transitory computer-readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by one or more processors of an electronic device, cause the electronic device to:

receive context information associated with a current word, wherein the context information includes one or more words stored on the electronic device;

determine, for each of a plurality of languages, a set of monolingual probabilities based on the context information;

determine a set of language weights based on the context information;

determine a set of multilingual probabilities based on the respective sets of monolingual probabilities and the set of language weights; and

provide, on a display of the electronic device, a plurality of candidate words based on the set of multilingual probabilities.

16. A method for providing candidate words, comprising:

at an electronic device having one or more processors, a display, and memory:

receiving context information associated with a current word, wherein the context information includes one or more words stored on the electronic device;

determining, for each of a plurality of languages, a set of monolingual probabilities based on the context information;

determining a set of language weights based on the context information;

determining a set of multilingual probabilities based on the respective sets of monolingual probabilities and the set of language weights; and

providing, on the display, a plurality of candidate words based on the set of multilingual probabilities.

17. The electronic device of claim 1 , wherein determining, for each of a plurality of languages, a set of monolingual probabilities based on the context information further comprises:

determining, based on the one or more words stored on the electronic device, a usage amount for each of the plurality of languages.

18. The electronic device of claim 17 , wherein determining, based on the one or more words stored on the electronic device, a usage amount for each of the plurality of languages further comprises:

determining a word count of each language.

19. The electronic device of claim 17 , wherein determining, based on the one or more words stored on the electronic device, a usage amount for each of the plurality of languages further comprises:

classifying one or more stored messages according to a dominant language of the messages.

20. The electronic device of claim 1 , wherein the one or more words stored on the electronic device are words of a message exchanged between at least two users.