Learning Determinantal Point Processes

Abstract

Determinantal point processes (DPPs), which arise in random matrix theory and quantum physics, are natural models for subset selection problems where diversity is preferred. Among many remarkable properties, DPPs offer tractable algorithms for exact inference, including computing marginal probabilities and sampling; however, an important open question has been how to learn a DPP from labeled training data. In this paper we propose a natural feature-based parameterization of conditional DPPs, and show how it leads to a convex and efficient learning formulation. We analyze the relationship between our model and binary Markov random fields with repulsive potentials, which are qualitatively similar but computationally intractable. Finally, we apply our approach to the task of extractive summarization, where the goal is to choose a small subset of sentences conveying the most important information from a set of documents. In this task there is a fundamental tradeoff between sentences that are highly relevant to the collection as a whole, and sentences that are diverse and not repetitive. Our parameterization allows us to naturally balance these two characteristics. We evaluate our system on data from the DUC 2003/04 multi-document summarization task, achieving state-of-the-art results.

References in corpus (1)

• Determinantal Processes and Independence

Cited by in corpus (34)

• Learning Mixtures of Submodular Shells with Application to Document Summarization
• Video Summarization with Long Short-term Memory
• Learning the Parameters of Determinantal Point Process Kernels
• Summary Transfer: Exemplar-based Subset Selection for Video Summarization
• Training Gaussian Boson Sampling Distributions
• Efficient Sampling for k-Determinantal Point Processes
• Expectation-Maximization for Learning Determinantal Point Processes
• Fixed-point algorithms for learning determinantal point processes
• Learning Policies for Contextual Submodular Prediction
• Large-Margin Determinantal Point Processes
• What comes next? Extractive summarization by next-sentence prediction
• Low-Rank Factorization of Determinantal Point Processes for Recommendation
• Scoring Sentence Singletons and Pairs for Abstractive Summarization
• GDPP: Learning Diverse Generations Using Determinantal Point Process
• Improving the Similarity Measure of Determinantal Point Processes for Extractive Multi-Document Summarization
• Scalable Learning and MAP Inference for Nonsymmetric Determinantal Point Processes
• Deep Determinantal Point Processes
• How Local is the Local Diversity? Reinforcing Sequential Determinantal Point Processes with Dynamic Ground Sets for Supervised Video Summarization
• Detecting (Un)Important Content for Single-Document News Summarization
• Some Inapproximability Results of MAP Inference and Exponentiated Determinantal Point Processes
• Composable Core-sets for Determinant Maximization: A Simple Near-Optimal Algorithm
• Faster Greedy MAP Inference for Determinantal Point Processes
• Better Highlighting: Creating Sub-Sentence Summary Highlights
• Determinantal Point Process as an alternative to NMS
• Video Summarization via Actionness Ranking
• Graphical structure of conditional independencies in determinantal point processes
• Multi-Document Summarization with Determinantal Point Processes and Contextualized Representations
• SgSum: Transforming Multi-document Summarization into Sub-graph Selection
• Towards Bursting Filter Bubble via Contextual Risks and Uncertainties
• Testing Determinantal Point Processes
• The Bayesian Low-Rank Determinantal Point Process Mixture Model
• Repulsive Mixture Models of Exponential Family PCA for Clustering
• Diverse Online Feature Selection
• A Comprehensive Attempt to Research Statement Generation