Generating a Targeted Summary of Textual Content Tuned to a Target Audience Vocabulary

In a digital medium environment to generate a targeted summary of textual content tuned to a target audience vocabulary, a method implemented by at least one computing device, the method comprising:

• receiving, by the at least one computing device, a request to generate the targeted summary of textual content tuned to the target audience vocabulary;
• generating, by a word generation model, an attention distribution comprising words from the textual content and the target audience vocabulary and selection probability values for each word in the attention distribution, the selection probability values indicating a respective probability for each word of being selected as the next word for the targeted summary of the textual content;
• selecting the next word for the targeted summary based on the attention distribution and a linguistic preference model indicating word preference probabilities for the target audience vocabulary;
• and
• providing feedback of the selected next word to the word generation model, the feedback causing the word generation model to modify the attention distribution for selection of subsequent words of the targeted summary based on the feedback of the next generated word.