Volgen
Bryan Eikema
Bryan Eikema
Natural Language Processing Researcher, University of Amsterdam
Geverifieerd e-mailadres voor uva.nl - Homepage
Titel
Geciteerd door
Geciteerd door
Jaar
Is MAP Decoding All You Need? The Inadequacy of the Mode in Neural Machine Translation
B Eikema, W Aziz
arXiv preprint arXiv:2005.10283, 2020
992020
Auto-Encoding Variational Neural Machine Translation
B Eikema, W Aziz
arXiv preprint arXiv:1807.10564, 2018
422018
Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translation
B Eikema, W Aziz
arXiv preprint arXiv:2108.04718, 2021
242021
Sampling-based approximations to minimum Bayes risk decoding for neural machine translation
B Eikema, W Aziz
Proceedings of the 2022 Conference on Empirical Methods in Natural Language …, 2022
152022
An approximate sampler for energy-based models with divergence diagnostics
B Eikema, G Kruszewski, CR Dance, H Elsahar, M Dymetman
Transactions of Machine Learning Research, 2022
62022
The Effect of Generalisation on the Inadequacy of the Mode
B Eikema
Proceedings of the 1st Workshop on Uncertainty-Aware NLP (UncertaiNLP 2024 …, 2024
2024
SAMPLING FROM DISCRETE ENERGY-BASED MODELS WITH QUALITY/EFFICIENCY TRADE-OFF
B Eikema, G Kruszewski, H Elsahar, S Clinchant, M Dymetman
US Patent App. 17/877,336, 2024
2024
Het systeem kan de bewerking nu niet uitvoeren. Probeer het later opnieuw.
Artikelen 1–7