Generating summaries tailored to target characteristics

TL;DR

This paper offers a comprehensive categorization of user preferences in text summarization, providing guidelines for integrating content and stylistic characteristics into sequence-to-sequence models, demonstrated through experiments on topics, readability, and simplicity.

Contribution

It introduces a holistic framework categorizing summary characteristics and offers guidelines for their incorporation into summarization models, addressing a gap in personalized summarization research.

Findings

Incorporating topic, readability, and simplicity improves summary quality.

Guidelines for integrating various characteristics enhance sequence-to-sequence summarization.

Experimental results validate the proposed prescriptions.

Abstract

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