Name: GeorgeVern
Type: User
Bio: Ph.D. student at EPFL/EDEE and HEIG-VD working on Machine Translation. Obtained MSc in DS and ML, and diploma in Computer Engineering from NTUA.
Twitter: gvernikos
Location: Lausanne, Switzerland
Blog: https://georgevern.github.io/
GeorgeVern's Projects
Python source code for EMNLP 2020 Findings paper: "Domain Adversarial Fine-Tuning as an Effective Regularizer".
A beautiful, simple, clean, and responsive Jekyll theme for academics
Code for the EACL 2024 paper: "Small Language Models Improve Giants by Rewriting Their Outputs"
MASS: Masked Sequence to Sequence Pre-training for Language Generation
This repo contains the code for the paper "Don't Rank, Combine! Combining Machine Translation Hypotheses Using Quality Estimation"
A software for transferring pre-trained English models to foreign languages
Python source code for EMNLP 2020 paper "Reusing a Pretrained Language Model on Languages with Limited Corpora for Unsupervised NMT".
Python source code for EMNLP 2021 Findings paper: "Subword Mapping and Anchoring Across Languages".
Unsupervised Word Segmentation for Neural Machine Translation and Text Generation
🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.
A framework to learn cross-lingual word embedding mappings