Users expend substantial time and mental effort in trying to distill the most important facts and/or insight from lengthy text content. While deep learning models can summarize long documents, such models typically operate on the backend. Model output is not customizable by end users via simple user interfaces. This disclosure describes mechanisms that provide users with the ability to obtain customized automatic summaries of documents. Users can specify the desired properties of the summaries based on their preferences and constraints such as available time, desired length or style for the summary, output language, complexity, etc. via convenient UI elements. Users can also choose to obtain automatically generated images or other media that summarize the document content. Customization of output can make the automatically generated summary more relevant and useful and save the user time and effort in reading lengthy text.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.