Hone as You Read: A Practical Type of Interactive Summarization

TL;DR

HARE introduces an interactive, minimally-invasive summarization method that adapts document summaries in real-time based on reader feedback, enhancing personalized reading experiences without disrupting flow.

Contribution

This work presents HARE, a novel interactive summarization task that uses real-time feedback to personalize summaries during reading, with new evaluation metrics and approaches.

Findings

Preference-learning approaches outperform heuristics

Real-time feedback improves summary relevance

Human evaluation confirms practicality

Abstract

We present HARE, a new task where reader feedback is used to optimize document summaries for personal interest during the normal flow of reading. This task is related to interactive summarization, where personalized summaries are produced following a long feedback stage where users may read the same sentences many times. However, this process severely interrupts the flow of reading, making it impractical for leisurely reading. We propose to gather minimally-invasive feedback during the reading process to adapt to user interests and augment the document in real-time. Building off of recent advances in unsupervised summarization evaluation, we propose a suitable metric for this task and use it to evaluate a variety of approaches. Our approaches range from simple heuristics to preference-learning and their analysis provides insight into this important task. Human evaluation additionally supports the practicality of HARE. The code to reproduce this work is available at https://github.com/tannerbohn/HoneAsYouRead.