A Temporally Sensitive Submodularity Framework for Timeline Summarization

TL;DR

This paper introduces a novel framework that adapts submodular optimization models from multi-document summarization to effectively handle timeline summarization by incorporating temporal dynamics, maintaining model advantages.

Contribution

It presents a flexible, scalable submodular framework for timeline summarization that preserves the benefits of MDS models while explicitly modeling temporal dependencies.

Findings

Framework achieves competitive performance in TLS tasks.

Retains scalability and theoretical guarantees of submodular models.

Open-source implementation available online.

Abstract

Timeline summarization (TLS) creates an overview of long-running events via dated daily summaries for the most important dates. TLS differs from standard multi-document summarization (MDS) in the importance of date selection, interdependencies between summaries of different dates and by having very short summaries compared to the number of corpus documents. However, we show that MDS optimization models using submodular functions can be adapted to yield well-performing TLS models by designing objective functions and constraints that model the temporal dimension inherent in TLS. Importantly, these adaptations retain the elegance and advantages of the original MDS models (clear separation of features and inference, performance guarantees and scalability, little need for supervision) that current TLS-specific models lack. An open-source implementation of the framework and all models described in this paper is available online.