@InProceedings{gholipourghalandari:2017:FrontiersSummarization,
  author    = {Gholipour Ghalandari, Demian},
  title     = {Revisiting the Centroid-based Method: A Strong Baseline for Multi-Document Summarization},
  booktitle = {Proceedings of the Workshop on New Frontiers in Summarization},
  month     = {September},
  year      = {2017},
  address   = {Copenhagen, Denmark},
  publisher = {Association for Computational Linguistics},
  pages     = {85--90},
  abstract  = {The centroid-based model for extractive document summarization is a simple and
	fast baseline that ranks sentences based on their similarity to a centroid
	vector. In this paper, we apply this ranking to possible summaries instead of
	sentences and use a simple greedy algorithm to find the best summary.
	Furthermore, we show possibilities to scale up to larger input document
	collections by selecting a small number of sentences from each document prior
	to constructing the summary.
	Experiments were done on the DUC2004 dataset for multi-document summarization.
	We observe a higher performance over the original model, on par with more
	complex state-of-the-art methods.},
  url       = {http://www.aclweb.org/anthology/W17-4511}
}