A Unified Framework for Generic, Query-Focused, Privacy Preserving and Update Summarization using Submodular Information Measures

TL;DR

This paper introduces a unified submodular information measure framework for various summarization tasks, demonstrating its effectiveness across different settings and datasets, including images, with potential for extension to videos and documents.

Contribution

It presents a unified approach using submodular information measures for generic, query-focused, privacy-sensitive, and update summarization, unifying prior disparate methods.

Findings

Previous techniques are special cases of the proposed submodular measures.

The framework effectively models different summarization tasks in experiments.

The approach generalizes well to real-world datasets and can extend to other media types.

Abstract

We study submodular information measures as a rich framework for generic, query-focused, privacy sensitive, and update summarization tasks. While past work generally treats these problems differently ({\em e.g.}, different models are often used for generic and query-focused summarization), the submodular information measures allow us to study each of these problems via a unified approach. We first show that several previous query-focused and update summarization techniques have, unknowingly, used various instantiations of the aforesaid submodular information measures, providing evidence for the benefit and naturalness of these models. We then carefully study and demonstrate the modelling capabilities of the proposed functions in different settings and empirically verify our findings on both a synthetic dataset and an existing real-world image collection dataset (that has been extended by adding concept annotations to each image making it suitable for this task) and will be publicly released. We employ a max-margin framework to learn a mixture model built using the proposed instantiations of submodular information measures and demonstrate the effectiveness of our approach. While our experiments are in the context of image summarization, our framework is generic and can be easily extended to other summarization settings (e.g., videos or documents).