Camilla Casula

Postdoc

    Short bio

    My research interests include (but are not limited to):


    • Fairness and bias issues in NLP

    • Synthetic data for subjective NLP tasks

    • NLP for social media and non-standard language

    • Qualitative analyses of both data and model outputs


    Previously, I was a PhD student at University of Trento and Fondazione Bruno Kessler, under the supervision of Sara Tonelli. My PhD was focused on the strengths and weaknesses of using synthetic data for abusive language detection online. Before that, I graduated from the Master’s Degree in Language Technology at Uppsala University (2020) with a thesis titled “Transfer Learning for Multilingual Offensive Language Detection with BERT”, co-supervised by Christian Hardmeier and Sara Tonelli.

    Activities

    I co-organized the GeoLingIt shared task @ Evalita 2023, focused on the geolocation of linguistic variation in social media posts in Italy.

    Main publications

    [Accepted @ EMNLP 2024] Camilla Casula, Sebastiano Vecellio Salto, Alan Ramponi, and Sara Tonelli. Delving into Qualitative Implications of Synthetic Data for Hate Speech Detection. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. To appear. Association for Computational Linguistics.

    Alan Ramponi*, Camilla Casula*, and Stefano Menini. 2024. Variationist: Exploring Multifaceted Variation and Bias in Written Language Data. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), pages 346–354, Bangkok, Thailand. Association for Computational Linguistics.

    Camilla Casula, Elisa Leonardelli, and Sara Tonelli. 2024. Don’t Augment, Rewrite? Assessing Abusive Language Detection with Synthetic Data. In Findings of the Association for Computational Linguistics ACL 2024, pages 11240–11247, Bangkok, Thailand. Association for Computational Linguistics.

    Tanise Ceron and Camilla Casula. Exploiting Contextualized Word Representations to Profile Haters on Twitter. In CLEF (Working Notes). 2021.

    Camilla Casula. Transfer Learning for Multilingual Offensive Language Detection with BERT. Master’s thesis, Uppsala University, Department of Linguistics and Philology, 2020.

    Publications

    1. Casula, Camilla; Tonelli, Sara,
      Generation-Based Data Augmentation for Offensive Language Detection: Is It Worth It?,
      Proceedings of the 17th Conference of the European Chapter of theAssociation for Computational Linguistics, {EACL} 2023, Dubrovnik,Croatia, May 2-6, 2023,
      Association for Computational Linguistics,
      2023
      , pp. 3359-
      3377
    2. Ramponi, Alan; Casula, Camilla,
      DiatopIt: A Corpus of Social Media Posts for the Study of Diatopic Language Variation in Italy,
      Proceedings of Tenth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2023),
      Association for Computational Linguistics,
      2023
      , pp. 187-
      199
    3. Ramponi, Alan; Casula, Camilla,
      GeoLingIt at EVALITA 2023: Overview of the Geolocation of Linguistic Variation in Italy Task,
      Proceedings of the Eighth Evaluation Campaign of Natural Language Processing and Speech Tools for Italian,
      2023
    4. Leonardelli, Elisa; Casula, Camilla,
      DH-FBK at SemEval-2023 Task 10: Multi-Task Learning with Classifier Ensemble Agreement for Sexism Detection,
      Proceedings of the The 17th International Workshop on Semantic Evaluation (SemEval-2023),
      2023
    5. Leonardelli, Elisa; Casula, Camilla,
      DH-FBK at HODI: Multi-Task Learning with Classifier Ensemble Agreement, Oversampling and Synthetic Data,
      Proceedings of EVALITA 2023: 8th Evaluation Campaign of Natural Language Processing and Speech Tools for Italian,
      vol. 3473,
      2023
    6. Casula, Camilla; Tonelli, Sara,
      Hate Speech Detection with Machine-Translated Data: The Role of Annotation Scheme, Class Imbalance and Undersampling,
      Proceedings of the Seventh Italian Conference on Computational Linguistics,CLiC-it 2020, Bologna, Italy, March 1-3, 2021,
      CEUR-WS.org,
      vol. 2769,
      2020
    7. Casula, Camilla; Palmero Aprosio, Alessio; Menini, Stefano; Tonelli, Sara,
      FBK-DH at SemEval-2020 Task 12: Using Multi-channel BERT for Multilingual Offensive Language Detection,
      Proceedings of the Fourteenth Workshop on Semantic Evaluation (SemEval 2020),
      International Committee for Computational Linguistics,
      2020
      , pp. 1539-
      1545