| 摘要 |
One embodiment of the present invention provides a system for placing linguistically-aware variables in computer-generated text. During operation, the system receives a sentence at a computer system, wherein the sentence comprises two or more words. Next, the system analyzes the sentence to identify a first variable, wherein the first variable is a place-holder for a first word. The system then receives the first word. After that, the system automatically determines a gender of the first word. Next, the system analyzes the sentence to identify a first dependent word that is dependent on the first word, wherein a spelling of the first dependent word is dependent on the gender of the first word. The system then determines the spelling of the first dependent word that corresponds to the gender of the first word. Next, the system replaces the first variable in the sentence with the first word. If necessary, the system modifies the spelling of the first dependent word in the sentence to match the gender of the first word. Finally, the system outputs the sentence.
|
