Publications

• Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages.
  Imani A., Lin P., Kargaran A.H., Severini S.*, Sabet M.J., Kassner N., Ma C., Schmid H., Martins A.F., Yvon F., Schütze H.
  ACL, 2023.
  [Paper] [Repo] [Models]
• Graph-Based Multilingual Label Propagation for Low-Resource Part-of-Speech Tagging.
  Imani A.*, Severini S.*, Sabet M.J., Yvon F., Schütze H.
  EMNLP, 2022.
  [Paper] [Repo]
• SilverAlign: MT-Based Silver Data Algorithm For Evaluating Word Alignment.
  Köksal A., Severini S., Schütze H.
  arXiv preprint arXiv:2210.06207, 2022.
  [Paper] [Repo]
• Towards a Broad Coverage Named Entity Resource: A Data-Efficient Approach for Many Diverse Languages.
  Severini S., Imani A., Dufter P., Schütze H.
  LREC, 2022.
  [Paper] [Slides] [Dataset]
• Don't Forget Cheap Training Signals Before Building Unsupervised Bilingual Word Embeddings.
  Severini S., Hangya V., Sabet M.J., Fraser A., Schütze H.
  BUCC@LREC, 2022.
  [Paper] [Slides] [Resource]
• CodeTrans: Towards Cracking the Language of Silicone's Code Through Self-Supervised Deep Learning and High Performance Computing.
  Elnaggar A, Ding W, Jones L, Gibbs T, Feher T, Angerer C, Severini S, Matthes F, Rost B.
  arXiv preprint arXiv:2104.02443 , 2021.
  [Paper] [Repo]
• Combining Word Embeddings with Bilingual Orthography Embeddings for Bilingual Dictionary Induction.
  Severini S., Hangya V., Fraser A., Schütze H.
  COLING, 2020.
  [Paper] [Poster]
• LMU Bilingual Dictionary Induction System with Word Surface Similarity Scores for BUCC 2020.
  Severini S.*, Hangya V.*, Fraser A., Schütze H.
  BUCC@LREC, 2020.
  [Paper]
• A Comparative Study of Models for Answer Sentence Selection.
  Rossetto F.*, Gravina A.*, Severini S.*, Attardi A.*.
  CLiC-it, 2019.
  [Paper]
• Cross Attention for Selection-based Question Answering.
  Gravina A.*, Rossetto F.*, Severini S.*, Attardi G.
  NL4AI@AI*IA, 2018.
  [Paper]