Interactive Editing for Text Summarization

TL;DR

REVISE is an interactive framework that enables human writers to iteratively refine and customize text summaries by editing segments and generating coherent alternatives, combining AI assistance with human expertise.

Contribution

The paper introduces REVISE, a novel iterative editing framework for personalized summarization, featuring a fill-in-the-middle model and new evaluation metrics tailored for collaborative summary refinement.

Findings

REVISE allows seamless segment editing and refinement.

The framework improves summary quality through iterative human-AI collaboration.

Novel evaluation metrics effectively assess personalized summarization quality.

Abstract

Summarizing lengthy documents is a common and essential task in our daily lives. Although recent advancements in neural summarization models can assist in crafting general-purpose summaries, human writers often have specific requirements that call for a more customized approach. To address this need, we introduce REVISE (Refinement and Editing via Iterative Summarization Enhancement), an innovative framework designed to facilitate iterative editing and refinement of draft summaries by human writers. Within our framework, writers can effortlessly modify unsatisfactory segments at any location or length and provide optional starting phrases -- our system will generate coherent alternatives that seamlessly integrate with the existing summary. At its core, REVISE incorporates a modified fill-in-the-middle model with the encoder-decoder architecture while developing novel evaluation metrics tailored for the summarization task. In essence, our framework empowers users to create high-quality, personalized summaries by effectively harnessing both human expertise and AI capabilities, ultimately transforming the summarization process into a truly collaborative and adaptive experience.