Preslav Nakov

Latest

• On the Effect of Dropping Layers of Pre-trained Transformer Models
• Fighting the COVID-19 Infodemic in Social Media: A Holistic Perspective and a Call to Arms
• Compressing Large-Scale Transformer-Based Models: A Case Study on BERT
• One Size Does Not Fit All: Comparing NMT Representations of Different Granularities
• QCN Egyptian Arabic to English MachineTranslation System for NIST OpenMT15
• Unsupervised word segmentation improves dialectal Arabic to English machine translation
• QCRI at IWSLT 2013: Experiments in Arabic-English and English-Arabic Spoken Language Translation