Bryan Eikema

14 papers A* 2B 1Journal 9Unranked 2
YearRankTypeTitle / Venue / Authors
2025 A* conf
Structure-Conditional Minimum Bayes Risk Decoding.
EMNLP
Bryan Eikema, Anna Rutkiewicz, Mario Giulianelli
2025 J jnl
Structure-Conditional Minimum Bayes Risk Decoding.
CoRR
Bryan Eikema, Anna Rutkiewicz, Mario Giulianelli
2025 J jnl
Teaching Language Models to Faithfully Express their Uncertainty.
CoRR
Bryan Eikema, Evgenia Ilia, José G. C. de Souza, Chrysoula Zerva, Wilker Aziz
2024 — conf
Findings of the WMT 2024 Shared Task on Chat Translation.
WMT
Wafaa Mohammed, Sweta Agrawal, M. Amin Farajian, Vera Cabarrão, Bryan Eikema, Ana C. Farinha, José Guilherme Camargo de Souza
2024 J jnl
Findings of the WMT 2024 Shared Task on Chat Translation.
CoRR
Wafaa Mohammed, Sweta Agrawal, M. Amin Farajian, Vera Cabarrão, Bryan Eikema, Ana C. Farinha, José G. C. de Souza
2022 J jnl
An approximate sampler for energy-based models with divergence diagnostics.
Trans. Mach. Learn. Res.
Bryan Eikema, Germán Kruszewski, Christopher R. Dance, Hady Elsahar, Marc Dymetman
2022 A* conf
Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translation.
EMNLP
Bryan Eikema, Wilker Aziz
2021 J jnl
Sampling from Discrete Energy-Based Models with Quality/Efficiency Trade-offs.
CoRR
Bryan Eikema, Germán Kruszewski, Hady Elsahar, Marc Dymetman
2021 J jnl
Sampling-Based Minimum Bayes Risk Decoding for Neural Machine Translation.
CoRR
Bryan Eikema, Wilker Aziz
2020 B conf
Is MAP Decoding All You Need? The Inadequacy of the Mode in Neural Machine Translation.
COLING
Bryan Eikema, Wilker Aziz
2020 J jnl
Is MAP Decoding All You Need? The Inadequacy of the Mode in Neural Machine Translation.
CoRR
Bryan Eikema, Wilker Aziz
2019 — conf
Auto-Encoding Variational Neural Machine Translation.
RepL4NLP@ACL
Bryan Eikema, Wilker Aziz
2018 J jnl
Auto-Encoding Variational Neural Machine Translation.
CoRR
Bryan Eikema, Wilker Aziz
2018 J jnl
Online Learning to Rank with List-level Feedback for Image Filtering.
CoRR
Chang Li, Artem Grotov, Ilya Markov, Bryan Eikema, Maarten de Rijke