Computer system methods for generating combined language content

1. A computer program stored in one or more non-transitory computer-readable mediums for generating code-switched content including words from at least two different languages, the computer program comprising instructions for performing the steps of:

(a) receiving by a processor a first input of a first language a user is fluent and a second input of a second language the user is not-fluent;

(b) generating by the processor content including a first language text based on the first input and a second language text based on the second input;

(c) aligning by the processor words of the first language text with a meaning the same as words of the second language text determined by a statistical machine translation (SMT) with parameters derived from bilingual text corpora, wherein a word ω e of the first language has a meaning that is the same as a word ω f of the second language wherein the aligning step is;

(d) presenting on a display interface the word ω f of the second language;

(e) receiving by the processor initial feedback from the user;

(f) calculating by the processor, based on the initial feedback, a recall probability value Pr(ω e ,ω f ) of a word pair (ω e ,ω f );

(g) selecting by the processor one or more words of the second language that have a maximum recall probability value;

(h) replacing a portion of the first language text with the one or more selected words of the second language to obtain combined content;

(i) presenting to the user the combined content as one or more selected from the group of: an audio stimulus, a graphic stimulus via the display interface, or a video stimulus via the display interface;

(j) receiving by the processor feedback from the user, wherein the feedback determines an actual recall probability value of each of the one or more selected words of the second language;

(k) updating the recall probability value of each of the one or more selected words of the second language with the actual recall probability value; and

(l) repeating steps (g)-(k).

2. The computer program stored in one or more non-transitory computer-readable mediums for generating code-switched content including words from at least two different languages according to claim 1 , wherein the replacing step further comprises the steps of:

estimating a vocabulary of the user;

computing a lexical translation probability between a word of the first language text and a word of the second language text; and

predicting a context probability of the one or more selected words of the second language appearing in the combined content.

3. The computer program stored in one or more non-transitory computer-readable mediums for generating code-switched content including words from at least two different languages according to claim 1 , wherein the first language text is a sentence.

4. The computer program stored in one or more non-transitory computer-readable mediums for generating code-switched content including words from at least two different languages according to claim 1 , wherein the first language text is a phrase.

5. The computer program stored in one or more non-transitory computer-readable mediums for generating code-switched content including words from at least two different languages according to claim 1 , wherein the first language text is a word.

6. The computer program stored in one or more non-transitory computer-readable mediums for generating code-switched content including words from at least two different languages according to claim 1 , wherein the feedback is implicit feedback in the form of gaze saccades.

7. The computer program stored in one or more non-transitory computer-readable mediums for generating code-switched content including words from at least two different languages according to claim 1 , wherein the recall probability value is factorized according to the following: Pr(ω e ,ω e )=Pr(ω e |ω f )Pr(ω e |context), where Pr(ω e |ω f ) is a lexical translation probability between ω e and ω f , and Pr(ω e |context) is a probability of ω e in the context of the sentence where ω e appears.

8. The computer program stored in one or more non-transitory computer-readable mediums for generating code-switched content including words from at least two different languages according to claim 7 , wherein the probability of ω e in the context of the sentence where ω e appears is computed using a linear combination of a tri-gram language model and a normalized latent semantic analysis (LSA) term-term similarity.

9. The computer program stored in one or more non-transitory computer-readable mediums for generating code-switched content including words from at least two different languages according to claim 1 , wherein the first language is English.

10. The computer program stored in one or more non-transitory computer-readable mediums for generating code-switched content including words from at least two different languages according to claim 1 , wherein the feedback determines whether or not the user knows the meaning of the word ω f of the second language and the feedback is one or more selected from the group of: a selection of an input, a self-paced or controlled reading speed, a number of page turns within a specified period of time, an eye-tracking such as gaze saccades, and facial expression monitoring.

11. The computer program stored in one or more non-transitory computer-readable mediums for generating code-switched content including words from at least two different languages according to claim 1 , wherein the display interface comprises one or more selected from the group of: a touch screen, a joystick, a trackball, a monitor, a speaker, a printer, a Google Glass® unit, a computer peripheral device capable of entering and/or viewing data, or any combination thereof.

12. The computer program stored in one or more non-transitory computer-readable mediums for generating code-switched content including words from at least two different languages according to claim 1 , wherein the selecting step further comprises the step of using the maximum recall probability value to determine a position for the one or more words of the second language.

13. The computer program stored in one or more non-transitory computer-readable mediums for generating code-switched content including words from at least two different languages according to claim 12 , wherein the position of the first language text is at a beginning of a sentence, a middle of a sentence, or an end of a sentence.