@InProceedings{min-freedman-meltzer:2017:EACLlong,
  author    = {Min, Bonan  and  Freedman, Marjorie  and  Meltzer, Talya},
  title     = {Probabilistic Inference for Cold Start Knowledge Base Population with Prior World Knowledge},
  booktitle = {Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers},
  month     = {April},
  year      = {2017},
  address   = {Valencia, Spain},
  publisher = {Association for Computational Linguistics},
  pages     = {601--612},
  abstract  = {Building knowledge bases (KB) automatically from text corpora is crucial for
	many applications such as question answering and web search. The problem is
	very challenging and has been divided into sub-problems such as mention and
	named entity recognition, entity linking and relation extraction. However,
	combining these components has shown to be under-constrained and often produces
	KBs with supersize entities and common-sense errors in relations (a person has
	multiple birthdates). The errors are difficult to resolve solely with IE tools
	but become obvious with world knowledge at the corpus level. By analyzing
	Freebase and a large text collection, we found that per-relation cardinality
	and the popularity of entities follow the power-law distribution favoring flat
	long tails with low-frequency instances. We present a probabilistic joint
	inference algorithm to incorporate this world knowledge during KB construction.
	Our approach yields state-of-the-art performance on the TAC Cold Start task,
	and 42% and 19.4% relative improvements in F1 over our baseline on Cold Start
	hop-1 and all-hop queries respectively.},
  url       = {http://www.aclweb.org/anthology/E17-1057}
}