@inproceedings{replicabilityanalysisfornaturallanguage,
  title = {Replicability Analysis for Natural Language Processing: Testing Significance with Multiple Datasets},
  author = {Rotem Dror and Gili Baumer and Marina Bogomolov and Roi Reichart},
  year = {2017},
  booktitle = {TACL 2017 1},
  eprint = {1709.09500},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1709.09500v1},
}