Publications

You can also find my articles on my Semantic Scholar or Google Scholar profile.

• AdapterSoup: Weight Averaging to Improve Generalization of Pretrained Language Models [slides]
  Alexandra Chronopoulou, Matthew E. Peters, Alexander Fraser, Jesse Dodge
  EACL 2023 (Findings)
  
• Language-Family Adapters for Low-Resource Multilingual Neural Machine Translation [slides]
  Alexandra Chronopoulou, Dario Stojanovski, Alexander Fraser
  EACL LoResMT workshop 2023
  
• Efficient Hierarchical Domain Adaptation for Pretrained Language Models [code] [blog] [slides]
  Alexandra Chronopoulou, Matthew E. Peters, Jesse Dodge
  NAACL 2022
  
• Improving the Lexical Ability of Pretrained Language Models for Unsupervised Neural Machine Translation [code]
  Alexandra Chronopoulou, Dario Stojanovski, Alexander Fraser
  NAACL 2021
  
• Reusing a Pretrained Language Model on Languages with Limited Corpora for Unsupervised NMT [code] [slides]
  Alexandra Chronopoulou, Dario Stojanovski, Alexander Fraser
  EMNLP 2020
  
• An Embarrassingly Simple Approach for Transfer Learning from Pretrained Language Models [code]
  Alexandra Chronopoulou, Christos Baziotis, Alexandros Potamianos
  NAACL 2019
  

• Jointly Optimizing Translations and Speech Timing to Improve Isochrony in Automatic Dubbing
  Alexandra Chronopoulou, Brian Thompson, Prashant Mathur, Yogesh Virkar, Surafel M. Lakew, Marcello Federico
  arxiv preprint
  
• Findings of the IWSLT 2023 Evaluation Campaign
  Milind Agarwal, ..., Alexandra Chronopoulou, et al. (50+ authors)
  IWSLT 2023
  
• Mitigating Data Imbalance and Representation Degeneration in Multilingual Machine Translation
  Wen Lai, Alexandra Chronopoulou, Alexander Fraser
  arxiv preprint
  
• On the Copying Problem of Unsupervised NMT: A Training Schedule with a Language Discriminator Loss
  Yihong Liu, Alexandra Chronopoulou, Hinrich Schutze, Alexander Fraser
  IWSLT 2023
  
• Improving Isochronous Machine Translation with Target Factors and Auxiliary Counters
  Proyag Pal, Brian Thompson, Yogesh Virkar, Prashant Mathur, Alexandra Chronopoulou, Marcello Federico
  INTERSPEECH 2023
  
• m⁴ Adapter: Multilingual Multi-Domain Adaptation for Machine Translation with a Meta-Adapter
  Wen Lai, Alexandra Chronopoulou, Alexander Fraser
  EMNLP 2022 (Findings)
  
• Domain Adversarial Fine-Tuning as an Effective Regularizer [code]
  Giorgos Vernikos, Katerina Margatina, Alexandra Chronopoulou, Ion Androutsopoulos
  EMNLP 2020 (Findings)
  
• The LMU Munich System for the WMT 2020 Unsupervised Machine Translation Shared Task [code] [slides] [poster]
  Alexandra Chronopoulou, Dario Stojanovski, Viktor Hangya, Alexander Fraser
  WMT 2020
  
• NTUA-SLP at IEST 2018: Ensemble of neural transfer methods for implicit emotion classification [code]
  Alexandra Chronopoulou, Katerina Margatina, Christos Baziotis, Alexandros Potamianos
  EMNLP WASSA workshop 2018
  
• NTUA-SLP at SemEval-2018 Task 1: Predicting Affective Content in Tweets with Deep Attentive RNNs and Transfer Learning [code]
  Christos Baziotis, Nikos Athanasiou, Alexandra Chronopoulou, Athanasia Kolovou, Georgios Paraskevopoulos, Nikolaos Ellinas, Shrikanth Narayanan, Alexandros Potamianos
  NAACL SemEval workshop 2018
  

• Transfer Learning with Deep Neural Networks for Sentiment Analysis and Semantic Modeling [thesis (in Greek)]
  Alexandra Chronopoulou
  National Technical University of Athens (NTUA)