Photo of Brian DuSell

Brian DuSell

/ˈbɹaɪən duˈsɛl/
杜亦然
デュセル・ブライアン

I am a PhD candidate in David Chiang's natural language processing research group at the University of Notre Dame. My primary research focus is on incorporating simulations of nondeterministic pushdown automata into neural networks to improve machine learning on human languages. My interests lie generally in syntax, machine translation, and neural networks.

News

  • The preprint for my new paper with David Chiang, "Learning Hierarchical Structures with Differentiable Nondeterministic Stacks," is now available on arXiv.
  • I'll be doing another summer internship with Amazon Translate!
  • I hosted a live Q&A session for my CoNLL paper, Learning Context-Free Languages with Nondeterministic Stack RNNs. Thanks for stopping by! Feel free to message me with questions any time.
  • I passed my oral candidacy! The topic was "Stack Nondeterminism in Neural Networks." A big thank-you to my committee members for their time and valuable feedback.
  • My paper with David Chiang, "Learning Context-Free Languages with Nondeterministic Stack RNNs", has been accepted to CoNLL 2020 and is now available on arXiv! The code is available on GitHub.
  • I've released an update to my semiring einsum package, a PyTorch package that allows you to do einsum in different semirings, with significant performance improvements and published it on PyPI. Just pip install torch-semiring-einsum!
  • I finished up a (remote) internship with the awesome Amazon Translate team in NYC. Thanks for a great summer!

Publications

  • Brian DuSell and David Chiang. 2021. Learning Hierarchical Structures with Differentiable Nondeterministic Stacks. In review for NeurIPS 2021. PDF 
    @misc{dusell-chiang-2021-learning,
    title={Learning Hierarchical Structures with Differentiable Nondeterministic Stacks}, 
    author={Brian DuSell and David Chiang},
    year={2021},
    eprint={2109.01982},
    archivePrefix={arXiv},
    primaryClass={cs.CL},
    note="In review for NeurIPS 2021."
}
  • Brian DuSell and David Chiang. 2020. Learning Context-Free Languages with Nondeterministic Stack RNNs. In Proceedings of the 24th Conference on Computational Natural Language Learning, pages 507–519, Online, November. Association for Computational Linguistics. PDF 
    @inproceedings{dusell-chiang-2020-learning,
    title = "Learning Context-Free Languages with Nondeterministic Stack {RNN}s",
    author = "DuSell, Brian  and
      Chiang, David",
    booktitle = "Proceedings of the 24th Conference on Computational Natural Language Learning",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2020.conll-1.41",
    pages = "507--519"
}
  • Kenton Murray, Brian DuSell, and David Chiang. 2019. Efficiency through Auto-Sizing: Notre Dame NLP’s Submission to the WNGT 2019 Efficiency Task. In Proceedings of the 3rd Workshop on Neural Generation and Translation, pages 297–301, Hong Kong, November. Association for Computational Linguistics. PDF 
    @inproceedings{murray-etal-2019-efficiency,
    title = "Efficiency through Auto-Sizing: {N}otre {D}ame {NLP}{'}s Submission to the {WNGT} 2019 Efficiency Task",
    author = "Murray, Kenton  and
      DuSell, Brian  and
      Chiang, David",
    booktitle = "Proceedings of the 3rd Workshop on Neural Generation and Translation",
    month = nov,
    year = "2019",
    address = "Hong Kong",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/D19-5634",
    doi = "10.18653/v1/D19-5634",
    pages = "297--301"
}

    • Education

    • University of Notre Dame logo

      University of Notre Dame

      2016-present
      Ph.D., Computer Science
      Advisor: David Chiang
    • University of Notre Dame logo

      University of Notre Dame

      2009-2013
      Bachelor of Science in Computer Science, magna cum laude

    Industry Experience

    • AWS logo

      Applied Scientist Intern

      Jun-Sep 2021
      Amazon Web Services
      Team: Amazon Translate
    • AWS logo

      Applied Scientist Intern

      Jun-Sep 2020
      Amazon Web Services
      Team: Amazon Translate
    • Oak Financial Software Corp. logo

      Software Developer

      2014-2016
      Oak Financial Software Corp.
    • NetApp logo

      Member of Technical Staff

      2013-2014
      NetApp
      Data Protection Group
    • Wolverine logo

      Software Engineering Intern

      Summer 2012
      Wolverine Trading

    Software

    • Nondeterministic Stack RNN

      PyTorch implementation of our Nondeterministic Stack RNN model, as well as other Stack RNN models.

    • Semiring Einsum

      Python package for efficiently performing einsum operations in different semirings in PyTorch.

    • Jishosen

      Online Japanese-English dictionary.

    See more on my GitHub page.

    Hey, you scrolled down this far!

    Fun fact: my grandfather, D. Lee DuSell, is an artist and sculptor, and you can check out his work on his website, made by yours truly.