Generating targeted summary of textual content tuned to target audience vocabulary

Abstract

A targeted summary of textual content tuned to a target audience vocabulary is generated in a digital medium environment. A word generation model obtains textual content, and generates a targeted summary of the textual content. During the generation of the targeted summary, the words of the targeted summary generated by the word generation model are tuned to the target audience vocabulary using alinguistic preference model. The linguistic preference model is trained, using machine learning on target audience training data corresponding to a corpus of text of the target audience vocabulary, tolearn word preferences of the target audience vocabulary between similar words (e.g., synonyms). After each word is generated using the word generation model and the linguistic preference model, feedback regarding the generated word is provided back to the word generation model. The feedback is utilized by the word generation model to generate subsequent words of the summary.

Description

Background technique [0001] Automatic summarization of text content can be used to save time for end users by providing an overview of text content (eg, documents or articles) that can be quickly read by the user. Traditional extractive summarization techniques extract key phrases from input text content, and then select a subset of these phrases to be placed in a summary. However, the summaries generated by these traditional summarization techniques are usually not human-like. Furthermore, some traditional summarization techniques generate summaries, which can then be "tuned" to the target audience as a post-processing step after generation of the summaries. However, adjusting a summary to a target audience after the summary has been generated often results in changing the meaning of the original text. For example, consider the sentence "The whole journey is bigger than the team". Based on the language preferences of the target audience, the word "total" may be preferred t...

AI Technical Summary

Problems solved by technology

Furthermore, existing summarization techniques fail to generate multiple summaries tuned to different target audience vocabularies

Images