Optimization-based Content Selection for Opinion Summarization

We introduce a content selection method for opinion summarization based on a well-studied, formal mathematical model, the p-median clustering problem from facility location theory. Our method replaces a series of local, myopic steps to content selection with a global solution, and is designed to allow content and realization decisions to be naturally integrated. We evaluate and compare our method against an existing heuristic-based method on content selection, using human selections as a gold standard. We find that the algorithms perform similarly, suggesting that our content selection method is robust enough to support integration with other aspects of summarization.