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
- Prompting Large Language Models with Human Error Markings for Self-Correcting Machine TranslationProceedings 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
- Enhancing Supervised Learning with Contrastive Markings in Neural Machine Translation TrainingProceedings 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
- Don’t Search for a Search Method – Simple Heuristics Suffice for Adversarial Text AttacksProceedings 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
- Sparse Perturbations for Improved Convergence in Stochastic Zeroth-Order OptimizationThe 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} }
- Correct Me If You Can: Learning from Error Corrections and MarkingsProceedings 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} }