no code implementations • WMT (EMNLP) 2021 • Àlex R. Atrio, Gabriel Luthier, Axel Fahy, Giorgos Vernikos, Andrei Popescu-Belis, Ljiljana Dolamic
We then present the application of this system to the 2021 task for low-resource supervised Upper Sorbian (HSB) to German translation, in both directions.
no code implementations • ICON 2021 • Àlex R. Atrio, Andrei Popescu-Belis
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.
no code implementations • 13 Jun 2019 • Àlex R. Atrio, Toni Badia, Jeremy Barnes
Current state-of-the-art models for sentiment analysis make use of word order either explicitly by pre-training on a language modeling objective or implicitly by using recurrent neural networks (RNNs) or convolutional networks (CNNs).
Cross-Lingual Sentiment Classification General Classification +4