Andréi Popescu-Belis
3 papers in the PaperMetrix corpus
Papers by this author
-
Small Batch Sizes Improve Training of Low-Resource Neural MT
2022 · arXiv (Cornell University)
We study the role of an essential hyper-parameter that governs the training of Transformers for neural machine translation in a low-resource setting: the batch size. Using theoretical insights and experimental evidence, we argue against the …
-
Sense-Aware Statistical Machine Translation using Adaptive Context-Dependent Clustering
2017 · Zenodo (CERN European Organization for Nuclear Research)
Statistical machine translation (SMT) systems use local cues from n-gram translation and language models to select the translation of each source word. Such systems do not explicitly perform word sense disambiguation (WSD), although this would …
-
Don’t Rank, Combine! Combining Machine Translation Hypotheses Using Quality Estimation
2024
Neural machine translation systems estimate probabilities of target sentences given source sentences, yet these estimates may not align with human preferences.This work introduces QE-fusion, a method that synthesizes translations using a quality estimation metric (QE), …