@InProceedings{ammar-EtAl:2018:N18-3,
  author    = {Ammar, Waleed  and  Groeneveld, Dirk  and  Bhagavatula, Chandra  and  Beltagy, Iz  and  Crawford, Miles  and  Downey, Doug  and  Dunkelberger, Jason  and  Elgohary, Ahmed  and  Feldman, Sergey  and  Ha, Vu  and  Kinney, Rodney  and  Kohlmeier, Sebastian  and  Lo, Kyle  and  Murray, Tyler  and  Ooi, Hsu-Han  and  Peters, Matthew  and  Power, Joanna  and  Skjonsberg, Sam  and  Wang, Lucy  and  Willhelm, Chris  and  Yuan, Zheng  and  van Zuylen, Madeleine  and  etzioni, oren},
  title     = {Construction of the Literature Graph in Semantic Scholar},
  booktitle = {Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 3 (Industry Papers)},
  month     = {June},
  year      = {2018},
  address   = {New Orleans - Louisiana},
  publisher = {Association for Computational Linguistics},
  pages     = {84--91},
  abstract  = {We describe a deployed scalable system for organizing published scientific literature into a heterogeneous graph to facilitate algorithmic manipulation and discovery. The resulting literature graph consists of more than 280M nodes, representing papers, authors, entities and various interactions between them (e.g., authorships, citations, entity mentions). We reduce literature graph construction into familiar NLP tasks (e.g., entity extraction and linking), point out research challenges due to differences from standard formulations of these tasks, and report empirical results for each task. The methods described in this paper are used to enable semantic features in www.semanticscholar.org.},
  url       = {http://www.aclweb.org/anthology/N18-3011}
}