I am a PhD student at the Institute for Logic, Language, and Computation at the University of Amsterdam. My interests lie at the intersection of natural language processing and probabilistic modelling. In particular I work on inducing latent structure in parallel data and improving neural machine translation through better probabilistic modelling. My research is part of the European GoURMET project. My thesis adviser is dr. Wilker Ferreira Aziz.

Current Interests


You can find my (slightly outdated) CV here.

Selected Publications

Sampling from Discrete Energy-Based Models with Quality/Efficiency Trade-offs
Bryan Eikema, Germán Kruszewski, Hady Elsahar, Marc Dymetman in arXiv, 2021

Sampling-Based Minimum Bayes Risk Decoding for Neural Machine Translation
Bryan Eikema and Wilker Aziz in arXiv, 2021

Is MAP Decoding All You Need? The Inadequacy of the Mode in Neural Machine Translation
Bryan Eikema and Wilker Aziz in Proceedings of the 28th International Conference on Computational Linguistics (COLING), 2020 Best Paper Award



AEVNMT.pt: A PyTorch-based framework for creating deep generative models of text.