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 • 12 Jan 2024 • Giorgos Vernikos, Andrei Popescu-Belis
We demonstrate that our approach generates novel translations in over half of the cases and consistently outperforms other methods across varying numbers of candidates (5-200).
1 code implementation • 2 Jun 2023 • Benoist Wolleb, Romain Silvestri, Giorgos Vernikos, Ljiljana Dolamic, Andrei Popescu-Belis
Subword tokenization is the de facto standard for tokenization in neural language models and machine translation systems.
1 code implementation • 22 May 2023 • Giorgos Vernikos, Arthur Bražinskas, Jakub Adamek, Jonathan Mallinson, Aliaksei Severyn, Eric Malmi
Despite the impressive performance of large language models (LLMs), they often lag behind specialized models in various tasks.
1 code implementation • 27 Sep 2022 • Giorgos Vernikos, Brian Thompson, Prashant Mathur, Marcello Federico
Our experimental results support our initial hypothesis and show that a simple extension of the metrics permits them to take advantage of context to resolve ambiguities in the reference.
1 code implementation • Findings (EMNLP) 2021 • Giorgos Vernikos, Andrei Popescu-Belis
State-of-the-art multilingual systems rely on shared vocabularies that sufficiently cover all considered languages.
Cross-Lingual Natural Language Inference Machine Translation +1
1 code implementation • EMNLP 2021 • Katerina Margatina, Giorgos Vernikos, Loïc Barrault, Nikolaos Aletras
Common acquisition functions for active learning use either uncertainty or diversity sampling, aiming to select difficult and diverse data points from the pool of unlabeled data, respectively.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Giorgos Vernikos, Katerina Margatina, Alexandra Chronopoulou, Ion Androutsopoulos
To address this issue, we introduce a new regularization technique, AFTER; domain Adversarial Fine-Tuning as an Effective Regularizer.