Nathan Berger, M.A.

I am a graduate student research assistant at the ICL and member of the Statistical Natural Language Processing Group.

Research Interests

  • Deep Learning
  • Reinforcement Learning
  • Machine Translation
  • Multilingual Models
  • Human Computer Interaction

Publications

2024

  1. Nathaniel Berger, Stefan Riezler, Miriam Exel and Matthias Huck
    Prompting Large Language Models with Human Error Markings for Self-Correcting Machine Translation
    Proceedings of the 25th Annual Conference of the European Association for Machine Translation, 2024
    @article{berger2024prompting,
      title = {Prompting Large Language Models with Human Error Markings for Self-Correcting Machine Translation},
      author = {Berger, Nathaniel and Riezler, Stefan and Exel, Miriam and Huck, Matthias},
      year = {2024},
      journal = {Proceedings of the 25th Annual Conference of the European Association for Machine Translation},
      url = {https://arxiv.org/pdf/2406.02267}
    }
    

2023

  1. Nathaniel Berger, Miriam Exel, Matthias Huck and Stefan Riezler
    Enhancing Supervised Learning with Contrastive Markings in Neural Machine Translation Training
    Proceedings of the 24th Annual Conference of the European Association for Machine Translation, Tampere, Finland, 2023
    @inproceedings{berger2023enhancing,
      title = {Enhancing Supervised Learning with Contrastive Markings in Neural Machine Translation Training},
      author = {Berger, Nathaniel and Exel, Miriam and Huck, Matthias and Riezler, Stefan},
      journal = {Proceedings of the 24th Annual Conference of the European Association for Machine Translation},
      city = {Tampere},
      country = {Finland},
      year = {2023},
      url = {https://arxiv.org/abs/2307.08416}
    }
    

2021

  1. Nathaniel Berger, Stefan Riezler, Artem Sokolov and Sebastian Ebert
    Don’t Search for a Search Method – Simple Heuristics Suffice for Adversarial Text Attacks
    Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP), Punta Cana, Dominican Republic, 2021
    @inproceedings{berger2021,
      author = {Berger, Nathaniel and Riezler, Stefan and Sokolov, Artem and Ebert, Sebastian},
      title = {Don't Search for a Search Method -- Simple Heuristics Suffice for Adversarial Text Attacks},
      journal = {Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing},
      journal-abbrev = {EMNLP},
      year = {2021},
      city = {Punta Cana},
      country = {Dominican Republic},
      url = {https://arxiv.org/abs/2109.07926}
    }
    

2020

  1. Mayumi Ohta, Nathaniel Berger, Artem Sokolov and Stefan Riezler
    Sparse Perturbations for Improved Convergence in Stochastic Zeroth-Order Optimization
    The 6th International Conference on Machine Learning, Optimization, and Data Science (LOD), Siena, Italy, 2020
    @article{ohta2020,
      author = {Ohta, Mayumi and Berger, Nathaniel and Sokolov, Artem and Riezler, Stefan},
      year = {2020},
      title = {Sparse Perturbations for Improved Convergence in Stochastic Zeroth-Order Optimization},
      journal = {The 6th International Conference on Machine Learning, Optimization, and Data Science},
      journal-abbrev = {LOD},
      city = {Siena, Italy},
      url = {https://arxiv.org/abs/2006.01759}
    }
    
  2. Julia Kreutzer, Nathaniel Berger and Stefan Riezler
    Correct Me If You Can: Learning from Error Corrections and Markings
    Proceedings of the 22nd Annual Conference of the European Association for Machine Translation (EAMT), Lisbon, Portugal, 2020
    @article{kreutzer2020a,
      author = {Kreutzer, Julia and Berger, Nathaniel and Riezler, Stefan},
      year = {2020},
      title = {Correct Me If You Can: Learning from Error Corrections and Markings},
      journal = {Proceedings of the 22nd Annual Conference of the European Association for Machine Translation},
      journal-abbrev = {EAMT},
      city = {Lisbon, Portugal},
      url = {https://arxiv.org/abs/2004.11222}
    }