Learning Mixtures of Submodular Shells with Application to Document Summarization
arXiv:1210.4871
Abstract
We introduce a method to learn a mixture of submodular "shells" in a large-margin setting. A submodular shell is an abstract submodular function that can be instantiated with a ground set and a set of parameters to produce a submodular function. A mixture of such shells can then also be so instantiated to produce a more complex submodular function. What our algorithm learns are the mixture weights over such shells. We provide a risk bound guarantee when learning in a large-margin structured-prediction setting using a projected subgradient method when only approximate submodular optimization is possible (such as with submodular function maximization). We apply this method to the problem of multi-document summarization and produce the best results reported so far on the widely used NIST DUC-05 through DUC-07 document summarization corpora.
Appears in Proceedings of the Twenty-Eighth Conference on Uncertainty in Artificial Intelligence (UAI2012)
References in corpus (2)
Cited by in corpus (26)
- Determinantal point processes for machine learning
- Black-Box Testing of Deep Neural Networks Through Test Case Diversity
- Personalized Bundle List Recommendation
- How to be Fair and Diverse?
- Abstractive Multi-Document Summarization via Phrase Selection and Merging
- TimeMachine: Timeline Generation for Knowledge-Base Entities
- Data Summarization at Scale: A Two-Stage Submodular Approach
- Kronecker Determinantal Point Processes
- Low-Rank Factorization of Determinantal Point Processes for Recommendation
- On Sampling and Greedy MAP Inference of Constrained Determinantal Point Processes
- Learning Determinantal Point Processes with Moments and Cycles
- Attention based Sentence Extraction from Scientific Articles using Pseudo-Labeled data
- Rates of estimation for determinantal point processes
- Maximum likelihood estimation of determinantal point processes
- Structured learning of sum-of-submodular higher order energy functions
- A Unified Framework for Generic, Query-Focused, Privacy Preserving and Update Summarization using Submodular Information Measures
- Exploiting local and global performance of candidate systems for aggregation of summarization techniques
- Earlier Isn't Always Better: Sub-aspect Analysis on Corpus and System Biases in Summarization
- Deep Submodular Networks for Extractive Data Summarization
- Graph Cuts with Interacting Edge Costs - Examples, Approximations, and Algorithms
- On the Relationship Between Probabilistic Circuits and Determinantal Point Processes
- Enumeration of Extractive Oracle Summaries
- Submodular Meta-Learning
- Demystifying Multi-Faceted Video Summarization: Tradeoff Between Diversity,Representation, Coverage and Importance
- Majorisation-minimisation algorithms for minimising the difference between lattice submodular functions
- An Algorithmic Theory of Dependent Regularizers, Part 1: Submodular Structure