Silvia Terragni

NLP Research Engineer.

2023

  • Silvia Terragni, Modestas Filipavicius, Nghia Khau, Bruna Guedes, André Manso and Roland Mathis: In-Context Learning User Simulators for Task-Oriented Dialog Systems. Foundations and Applications in Large-scale AI: Models-Pre-training, Fine-tuning, and Prompt-based Learning (co-located at KDD 2023) [https://arxiv.org/abs/2306.00774] [Code]

2022

  • Patrick John Chia, Giuseppe Attanasio, Federico Bianchi, Silvia Terragni, Ana Rita Magalhães, Diogo Goncalves, Ciro Greco, Jacopo Tagliabue: Contrastive language and vision learning of general fashion concepts Scientific reports 12 [https://doi.org/10.1038/s41598-022-23052-9] [Code]
  • Silvia Terragni, Bruna Guedes, Andre Manso, Modestas Filipavicius, Nghia Khau, Roland Mathis: BETOLD: A Task-Oriented Dialog Dataset for Breakdown Detection. Proceedings of the Second Workshop on When Creative AI Meets Conversational AI (co-located at COLING 2022) [https://aclanthology.org/2022.cai-1.4] [Code]

2021

  • Federico Bianchi, Giuseppe Attanasio, Raphael Pisoni, Silvia Terragni, Gabriele Sarti, Sri Lakshmi: Contrastive Language-Image Pre-Training for the Italian Language. Pre-print [https://arxiv.org/abs/2108.08688] [Code]
  • Silvia Terragni, Elisabetta Fersini, Enza Messina: Word Embbeding-based Topic Similarity Measures. The 26th International Conference on Natural Language & Information Systems (NLDB 2021). [https://link.springer.com/chapter/10.1007/978-3-030-80599-9_4] [Code]
  • Federico Bianchi Silvia Terragni, Dirk Hovy: Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherence The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2021) [https://aclanthology.org/2021.acl-short.96/] [Code]
  • Silvia Terragni, Elisabetta Fersini, Bruno Galuzzi, Pietro Tropeano, Antonio Candelieri: OCTIS: Comparing and Optimizing Topic models is Simple! Proceedings of the Demonstrations at the 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2021), (2021). [https://www.aclweb.org/anthology/2021.eacl-demos.31/] [Code]
  • Federico Bianchi Silvia Terragni, Dirk Hovy, Debora Nozza, Elisabetta Fersini: Cross-lingual Zero-shot Topic Models with Contextualized Embeddings. The 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2021), (2021). [https://www.aclweb.org/anthology/2021.eacl-main.143/] [Code]

2020

  • Silvia Terragni, Debora Nozza, Elisabetta Fersini, Enza Messina: Which Matters Most? Comparing the Impact of Concept and Document Relationships in Topic Models Proceedings of the First Workshop on Insights from Negative Results in NLP @ EMNLP2020 (2020). [10.18653/v1/2020.insights-1.5] [Code]
  • Federico Bianchi Silvia Terragni, Dirk Hovy, Debora Nozza, Elisabetta Fersini: Cross-lingual Contextualized Topic Models with Zero-shot Learning. Preprint (2020). [https://arxiv.org/abs/2004.07737] [Code]
  • Federico Bianchi Silvia Terragni, Dirk Hovy: Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherence. Preprint (2020). [https://arxiv.org/abs/2004.03974] [Code]
  • Silvia Terragni, Elisabetta Fersini, Enza Messina: Constrained Relational Topic Models. Information Sciences 512: 581-594 (2020). [10.1016/j.ins.2019.09.039] [Code]