Debora Nozza

Latest

• A Tale of Pronouns: Interpretability Informs Gender Bias Mitigation for Fairer Instruction-Tuned Machine Translation
• Wisdom of Instruction-Tuned Language Model Crowds. Exploring Model Label Variation
• A Multi-dimensional study on Bias in Vision-Language models
• MilaNLP at SemEval-2023 Task 10: Ensembling Domain-Adapted and Regularized Pretrained Language Models for Robust Sexism Detection
• Respectful or Toxic? Using Zero-Shot Learning with Language Models to Detect Hate Speech
• The State of Profanity Obfuscation in Natural Language Processing Scientific Publications
• What about ''em''? How Commercial Machine Translation Fails to Handle (Neo-)Pronouns
• What about ''em''? How Commercial Machine Translation Fails to Handle (Neo-)Pronouns
• A Cross-Lingual Study of Homotransphobia on Twitter
• Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale
• ferret: a Framework for Benchmarking Explainers on Transformers
• Measuring Harmful Representations in Scandinavian Language Models
• Data-Efficient Strategies for Expanding Hate Speech Detection into Under-Resourced Languages
• Is It Worth the (Environmental) Cost? Limited Evidence for the Benefits of Diachronic Continuous Training
• HATE-ITA: Hate Speech Detection in Italian Social Media Text
• Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Models
• MilaNLP at SemEval-2022 Task 5: Using Perceiver IO for Detecting Misogynous Memes with Text and Image Modalities
• Language Invariant Properties in Natural Language Processing
• Benchmarking Post-Hoc Interpretability Approaches for Transformer-based Misogyny Detection
• Measuring Harmful Sentence Completion in Language Models for LGBTQIA+ Individuals
• Pipelines for Social Bias Testing of Large Language Models
• XLM-EMO: Multilingual Emotion Prediction in Social Media Text
• Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists
• Exposing the limits of Zero-shot Cross-lingual Hate Speech Detection
• HONEST: Measuring Hurtful Sentence Completion in Language Models
• FEEL-IT: Emotion and Sentiment Classification for the Italian Language
• MilaNLP @ WASSA: Does BERT Feel Sad When You Cry?
• Cross-lingual Contextualized Topic Models with Zero-shot Learning
• What the [MASK]? Making Sense of Language-Specific BERT Models