10 citations · 14 across the 4 of their papers we have counts for
7 papers
Don't Rank, Combine! Combining Machine Translation Hypotheses Using Quality Estimation
Giorgos Vernikos, Andrei Popescu-Belis
Neural machine translation systems estimate probabilities of target sentences given source sentences, yet these estimates may not align with human preferences. This work introduces…
Assessing the Importance of Frequency versus Compositionality for Subword-based Tokenization in NMT
Benoist Wolleb, Romain Silvestri, Giorgos Vernikos +2
Subword tokenization is the de facto standard for tokenization in neural language models and machine translation systems. Three advantages are frequently cited in favor of subwords…
Small Language Models Improve Giants by Rewriting Their Outputs
Giorgos Vernikos, Arthur Bražinskas, Jakub Adamek +3
Despite the impressive performance of large language models (LLMs), they often lag behind specialized models in various tasks. LLMs only use a fraction of the existing training dat…
Embarrassingly Easy Document-Level MT Metrics: How to Convert Any Pretrained Metric Into a Document-Level Metric
Giorgos Vernikos, Brian Thompson, Prashant Mathur +1
We hypothesize that existing sentence-level machine translation (MT) metrics become less effective when the human reference contains ambiguities. To verify this hypothesis, we pres…
Subword Mapping and Anchoring across Languages
Giorgos Vernikos, Andrei Popescu-Belis
State-of-the-art multilingual systems rely on shared vocabularies that sufficiently cover all considered languages. To this end, a simple and frequently used approach makes use of…
Active Learning by Acquiring Contrastive Examples
Katerina Margatina, Giorgos Vernikos, Loïc Barrault +1
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, r…
Domain Adversarial Fine-Tuning as an Effective Regularizer
Giorgos Vernikos, Katerina Margatina, Alexandra Chronopoulou +1
In Natural Language Processing (NLP), pretrained language models (LMs) that are transferred to downstream tasks have been recently shown to achieve state-of-the-art results. Howeve…