@InProceedings{shirakawa-hara-maekawa:2017:EMNLP2017,
  author    = {Shirakawa, Masumi  and  Hara, Takahiro  and  Maekawa, Takuya},
  title     = {Never Abandon Minorities: Exhaustive Extraction of Bursty Phrases on Microblogs Using Set Cover Problem},
  booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing},
  month     = {September},
  year      = {2017},
  address   = {Copenhagen, Denmark},
  publisher = {Association for Computational Linguistics},
  pages     = {2358--2367},
  abstract  = {We propose a language-independent data-driven method to exhaustively extract
	bursty phrases of arbitrary forms (e.g., phrases other than simple noun
	phrases) from microblogs. The burst (i.e., the rapid increase of the
	occurrence) of a phrase causes the burst of overlapping N-grams including
	incomplete ones. In other words, bursty incomplete N-grams inevitably overlap
	bursty phrases. Thus, the proposed method performs the extraction of bursty
	phrases as the set cover problem in which all bursty N-grams are covered by a
	minimum set of bursty phrases. Experimental results using Japanese Twitter data
	showed that the proposed method outperformed word-based, noun phrase-based, and
	segmentation-based methods both in terms of accuracy and coverage.},
  url       = {https://www.aclweb.org/anthology/D17-1251}
}