Benjamin Van Durme
Benjamin Van Durme


Johns Hopkins University
Computer Science

Benjamin Van Durme is the lead of Text Research at the JHU HLTCOE. His group has developed an infrastructure for cross-language, cross-tool interoperability which we call Concrete.

Benjamin Van Durme

Refereed Publications


  1. B. Van Durme, T. Lippincott, K. Duh, D. Burchfield, A. Poliak, C. Costello, T. Finin, S. Miller, J. Mayfield, P. Koehn, C. Harmon, D. Lawrie, C. May, M. Thomas, A. Carrell, and J. Chaloux, "CADET: Computer Assisted Discovery Extraction and Translation", InProceedings, 8th International Joint Conference on Natural Language Processing (System Demonstrations), November 2017, 110 downloads.
  2. F. Ferraro, A. Poliak, R. Cotterell, and B. Van Durme, "Frame-Based Continuous Lexical Semantics through Exponential Family Tensor Factorization and Semantic Proto-Roles", InProceedings, Proceedings of the Sixth Joint Conference on Lexical and Computational Semantics (*SEM), August 2017, 54 downloads.


  1. F. Ferraro and B. Van Durme, "A Unified Bayesian Model of Scripts, Frames and Language.", InProceedings, Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, February 2016, 30 downloads.


  1. T. Wolfe, M. Dredze, J. Mayfield, P. McNamee, C. Harmon, T. Finin, and B. Van Durme, "Interactive Knowledge Base Population", Proceedings, arXiv:1506.00301 [cs.AI], May 2015, 497 downloads.