Learning Mixtures of Submodular Shells with Application to Document Summarization
This work addresses multi-document summarization for natural language processing applications, representing an incremental advance with specific performance gains.
The paper tackles the problem of learning mixtures of submodular shells in a large-margin setting to produce complex submodular functions, achieving the best reported results on the NIST DUC-05 through DUC-07 document summarization corpora.
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.