Generating summaries tailored to target characteristics
This work addresses the need for more holistic and customizable text summarization for users, but it is incremental as it builds on existing frameworks with new categorizations and guidelines.
The paper tackled the problem of generating text summaries tailored to user preferences by categorizing characteristics into content and style aspects, and provided guidelines for incorporating them into sequence-to-sequence frameworks, with experiments showing viability for topics, readability, and simplicity.
Recently, research efforts have gained pace to cater to varied user preferences while generating text summaries. While there have been attempts to incorporate a few handpicked characteristics such as length or entities, a holistic view around these preferences is missing and crucial insights on why certain characteristics should be incorporated in a specific manner are absent. With this objective, we provide a categorization around these characteristics relevant to the task of text summarization: one, focusing on what content needs to be generated and second, focusing on the stylistic aspects of the output summaries. We use our insights to provide guidelines on appropriate methods to incorporate various classes characteristics in sequence-to-sequence summarization framework. Our experiments with incorporating topics, readability and simplicity indicate the viability of the proposed prescriptions