Debora Nozza

Latest

• Measuring Harmful Representations in Scandinavian Language Models
• Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale
• Data-Efficient Strategies for Expanding Hate Speech Detection into Under-Resourced Languages
• The State of Profanity Obfuscation in Natural Language Processing Scientific Publications
• Is It Worth the (Environmental) Cost? Limited Evidence for the Benefits of Diachronic Continuous Training
• ferret: a Framework for Benchmarking Explainers on Transformers
• 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
• XLM-EMO: Multilingual Emotion Prediction in Social Media Text
• Exposing the limits of Zero-shot Cross-lingual Hate Speech Detection
• HONEST: Measuring Hurtful Sentence Completion in Language Models
• LearningToAdapt with word embeddings: Domain adaptation of Named Entity Recognition systems
• 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
• AMI @ EVALITA2020: Automatic Misogyny Identification
• Which Matters Most? Comparing the Impact of Concept and Document Relationships in Topic Models
• Profiling Italian Misogynist: An Empirical Study
• What the [MASK]? Making Sense of Language-Specific BERT Models
• CAGE: Constrained deep Attributed Graph Embedding
• Unintended Bias in Misogyny Detection
• Word Embeddings for Unsupervised Named Entity Linking
• SemEval-2019 Task 5: Multilingual Detection of Hate Speech Against Immigrants and Women in Twitter
• Overview of the Evalita 2018 Task on Automatic Misogyny Identification (AMI)
• Mapping Natural Language Labels to Structured Web Resources
• Towards encoding time in text-based entity embeddings
• UNIMIB@ NEEL-IT: Named Entity Recognition and Linking of Italian Tweets
• Adapting Named Entity Types to New Ontologies in a Microblogging Environment
• A Multi-View Sentiment Corpus
• Towards adaptation of named entity classification
• TWINE: A real-time system for TWeet analysis via INformation Extraction
• Deep learning and ensemble methods for Domain Adaptation
• Unsupervised Irony Detection: A Probabilistic Model with Word Embeddings
• A latent representation model for sentiment analysis in heterogeneous social networks