Samuel Wiseman

Assistant Professor of Computer Science

An assistant professor at Duke University’s Department of Computer Science, and he is interested in natural language processing and machine learning. Before Duke, he was a research assistant professor at TTIC, and before that a PhD student in Computer Science at Harvard, where he was advised by Sasha Rush and Stuart Shieber.

Contact Information

  • Office Location: D105 LSRC
  • Office Phone: (919) 660-6558
  • Email Address: swiseman at cs.duke.edu

Education

  • Ph.D., Harvard University, 2018
  • A.B., Princeton University, 2010

Research Interests

Sam Wiseman's research focuses on natural language processing. He is broadly interested in deep learning approaches to structured prediction for natural language processing problems, with a particular recent interest in structured approaches to text generation. Here are some selected publications:

  • ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation. Lifu Tu, Richard Yuanzhe Pang, Sam Wiseman, and Kevin Gimpel. ACL, 2020.
  • Amortized Bethe Free Energy Minimization for Learning MRFs. Sam Wiseman and Yoon Kim. NeurIPS, 2019.
  • Label-Agnostic Sequence Labeling by Copying Nearest Neighbors. Sam Wiseman and Karl Stratos. ACL, 2019.
  • A Multi-Task Approach for Disentangling Syntax and Semantics in Sentence Representations. Mingda Chen, Qingming Tang, Sam Wiseman, and Kevin Gimpel. NAACL, 2019.
  • Learning Neural Templates for Text Generation. Sam Wiseman, Stuart M. Shieber, and Alexander M. Rush. EMNLP, 2018.