Papers

2024

• Automatic Annotation of Dream Report’s Emotional Content with Large Language Models , Bertolini L., Elce V., Michalak A., Widhoelzl H-S., Bernardi G., Weeds J., In Proceedings of the Ninth Workshop on Computational Linguistics and Clinical Psychology, Malta. Association for Computational Linguistics 2024[code]

2023

• Towards Unsupervised Compositional Entailment with Multi-Graph Embedding Models, Bertolini L., Weeds J. Weir D., In Proceedings of the 15th International Conference on Computational Semantics (IWCS), Nancy, France, Association for Computational Linguistics 2023.
• Dreams Are More "Predictable" Than You Think , Bertolini L.[code]

2022

• Testing Large Language Models on Compositionality and Inference with Phrase-Level Adjective-Noun Entailment, Bertolini L.,Weeds J., Weir D., In Proceedings of the 29th International Conference on Computational Linguistics (COLING) 2022

2021

• Representing Syntax and Composition with Geometric Transformations, Bertolini L.,Weeds J., Weir D., Peng Q., In Findings of the Association for Computational Linguistics: ACL 2021
• Data Augmentation for Hypernymy Detection, Kober T., Weeds J., Bertolini L., Weir D., In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL)

Posters, presentations, and invited talks

2024

• Invited talk: Field of dreams: applying NLP to automatize dream content analysis; CBS Research Seminar, The Hong Kong Polytechnic University

2023

• Oral presentation: DReAMy: a library for the automatic analysis and annotation of dream reports with multilingual large language models. Bertolini L., Michalak A., Weeds J., World Sleep Congress (October) 2023. [code]
• Poster: AUTOMATIC AND INTERPRETABLE DREAM REPORTS ANNOTATION WITH TEXT-GENERATION LARGE LANGUAGE MODEL. Bertolini L., eSLEEP congress (October) 2023. [code]
• Invited talk: Transformers & Hugging Faces: Theory and Applications of NLP’s Most Notorious Architecture; Sussex Data Science Meet Up.

2022

• Invited talk: Testing Language Models on Compositionality; MilaNLP wekly seminar guest presenter.

2021

• Poster: Representing Syntax and Composition with Geometric Transformations, Bertolini L.,Weeds J., Weir D., Peng Q., Representation Learning for NLP (RepL4NLP) workshop, ACL 2021
• Invited talk: A Tale of Compositionality: from Humans to Machines; Guest talk to the University of Sussex Data Science Society

2019

• Poster: CoDE: Learning Composable Dependecy Embeddings Bertolini L., Weeds J. Weir D., VSDD workshop, 13th International Conference on Computational Semantics (IWCS) [code, data]