Bryan Eikema

According to our database, Bryan Eikema authored at least 7 papers between 2018 and 2022.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2022

An approximate sampler for energy-based models with divergence diagnostics.

Bryan Eikema, Germán Kruszewski, Christopher R. Dance, Hady Elsahar, Marc Dymetman

Trans. Mach. Learn. Res., 2022

Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translation.

Bryan Eikema, Wilker Aziz

Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022

2021

Sampling from Discrete Energy-Based Models with Quality/Efficiency Trade-offs.

Bryan Eikema, Germán Kruszewski, Hady Elsahar, Marc Dymetman

CoRR, 2021

Sampling-Based Minimum Bayes Risk Decoding for Neural Machine Translation.

Bryan Eikema, Wilker Aziz

CoRR, 2021

2020

Is MAP Decoding All You Need? The Inadequacy of the Mode in Neural Machine Translation.

Bryan Eikema, Wilker Aziz

Proceedings of the 28th International Conference on Computational Linguistics, 2020

2019

Auto-Encoding Variational Neural Machine Translation.

Bryan Eikema, Wilker Aziz

Proceedings of the 4th Workshop on Representation Learning for NLP, 2019

2018

Online Learning to Rank with List-level Feedback for Image Filtering.

Chang Li, Artem Grotov, Ilya Markov, Bryan Eikema, Maarten de Rijke

CoRR, 2018