Ruprecht-Karls-Universität Heidelberg

Julia Kreutzer

2017

  • A Shared Task on Bandit Learning for Machine Translation. A. Sokolov, J. Kreutzer, K. Sunderland, P. Danchenko, W. Szymaniak, H. Fürstenau, S. Riezler. Conference on Machine Translation (WMT) 2017. Copenhagen, Denmark. [ pdf | task page ]
  • Learning What's Easy: Fully Differentiable Neural Easy-First Decoders. André Martins, Julia Kreutzer. Conference on Empirical Methods in Natural Language (EMNLP) 2017. Copenhagen, Denmark. [ pdf | code ]
  • Bandit Structured Prediction for Neural Sequence-to-Sequence Learning. Julia Kreutzer, Artem Sokolov, Stefan Riezler. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL) 2017. Vancouver, Canada. [ pdf  |  code ]

2016

  • Stochastic Structured Prediction under Bandit Feedback. Artem Sokolov, Julia Kreutzer, Christopher Lo, Stefan Riezler. In Advances in Neural Information Processing Systems (NIPS). Barcelona, Spain. [ pdf |  code | video ]
  • Learning Structured Predictors from Bandit Feedback for Interactive NLP. Artem Sokolov, Julia Kreutzer, Christopher Lo, Stefan Riezler. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL). Berlin, Germany. [ pdf ]
  • Quality Estimation From Scratch. Julia Kreutzer. Master's Thesis. March 2016. [ pdf ]

2015

  • QUality Estimation from ScraTCH (QUETCH): Deep Learning for Word-level Translation Quality Estimation. Julia Kreutzer, Shigehiko Schamoni, Stefan Riezler. In Proceedings of the 10th Workshop on Machine Translation (WMT). Lisbon, Portugal. [ pdf | code ]

2014

  • Dimensionality Reduction in Semantic Vector Spaces Using a Derivational Resource. Julia Kreutzer. Bachelor's Thesis. July 2014. [ pdf ]