Papers by Enrico Liscio
What does a Text Classifier Learn about Morality? An Explainable Method for Cross-Domain Comparison of Moral Rhetoric (2023.acl-long)
Copied to clipboard
Enrico Liscio, Oscar Araque, Lorenzo Gatti, Ionut Constantinescu, Catholijn Jonker, Kyriaki Kalimeri, Pradeep Kumar Murukannaiah
| Challenge: | Existing methods to analyze whether a text classifier learns the domain-specific expression of moral language are lacking. |
| Approach: | They propose a method to compare a supervised classifier’s representation of moral rhetoric across domains by exploring similarities and differences between moral concepts and domains. |
| Outcome: | The proposed method compares a supervised classifier’s representation of moral rhetoric across domains and domains. |
Morality is Non-Binary: Building a Pluralist Moral Sentence Embedding Space using Contrastive Learning (2024.findings-eacl)
Copied to clipboard
| Challenge: | Existing NLP methods treat morality as binary, ranging from right to wrong. |
| Approach: | They propose to build a pluralist moral sentence embedding space using contrastive learning methods to examine relationships among moral elements. |
| Outcome: | The proposed method shows that pluralism can be captured in an embedding space. |
Cross-Domain Classification of Moral Values (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods to identify moral values in text can be challenging for transferring knowledge between domains. |
| Approach: | They compare a deep learning model with a domain-specific value classifier to find out whether it can transfer knowledge to new domains. |
| Outcome: | The proposed model can generalize and transfer knowledge to novel domains, but introduce catastrophic forgetting. |
Will Annotators Disagree? Identifying Subjectivity in Value-Laden Arguments (2025.findings-emnlp)
Copied to clipboard
| Challenge: | aggregating multiple annotations into a single ground truth label may hide valuable insights into disagreement . |
| Approach: | They propose methods for identifying subjectivity in recognizing human values that motivate arguments. |
| Outcome: | The proposed methods can help identify arguments that individuals may interpret differently. |
Annotator-Centric Active Learning for Subjective NLP Tasks (2024.emnlp-main)
Copied to clipboard
| Challenge: | Annotator-centric active learning addresses the high costs of collecting human annotations by strategically annotating the most informative samples. |
| Approach: | They propose annotator-centric active learning which incorporates an annotation strategy following data sampling to approximate the full diversity of human judgments. |
| Outcome: | The proposed approach improves data efficiency and performs well in annotator-centric evaluations. |