Knapsack Constrained Contextual Submodular List Prediction with Application to Multi-document Summarization

TL;DR

This paper introduces a novel approach for list prediction under knapsack constraints using submodular reward functions, demonstrating improved performance in multi-document summarization tasks.

Contribution

It adapts sequence prediction models to optimize greedy maximization under knapsack constraints via online learning, advancing multi-document summarization.

Findings

Outperforms state-of-the-art summarization methods

Effective adaptation of sequence prediction models to constrained optimization

Demonstrates the utility of submodular functions in list prediction

Abstract

We study the problem of predicting a set or list of options under knapsack constraint. The quality of such lists are evaluated by a submodular reward function that measures both quality and diversity. Similar to DAgger (Ross et al., 2010), by a reduction to online learning, we show how to adapt two sequence prediction models to imitate greedy maximization under knapsack constraint problems: CONSEQOPT (Dey et al., 2012) and SCP (Ross et al., 2013). Experiments on extractive multi-document summarization show that our approach outperforms existing state-of-the-art methods.