SOKLI EFFROSYNI

Ruolo:
Assegnista di ricerca
Settore scientifico disciplinare:
Informatica (INF/01)

Pubblicazioni

  • Sokli, E., Kasela, P., Peikos, G., Pasi, G. (In corso di stampa). Mixture of Experts Approaches in Dense Retrieval Tasks. In In Proceedings of the 2025 IEEE/WIC International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT 2025). Dettaglio

  • Sokli, E., Kasela, P., Peikos, G., Pasi, G. (2025). Investigating Mixture of Experts in Dense Retrieval. In Proceedings of the 15th Italian Information Retrieval Workshop (IIR 2025) (pp.101-107). CEUR-WS. Dettaglio

  • Kasela, P., Braga, M., Sokli, E., Milanese, G., Peikos, G., Modha, S., et al. (2025). Overview of the PIR Track at FIRE 2024: Evaluation of Personalised Information Retrieval. In FIRE '24: Proceedings of the 16th Annual Meeting of the Forum for Information Retrieval Evaluation (pp.11-13). Association for Computing Machinery [10.1145/3734947.3735665]. Dettaglio

  • Sokli, E., Peikos, G., Kasela, P., Pasi, G. (2025). Leveraging Cognitive Complexity of Texts for Contextualization in Dense Retrieval. In EMNLP 2025 - 2025 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference (pp.27083-27096). Association for Computational Linguistics [10.18653/v1/2025.emnlp-main.1377]. Dettaglio

  • Sokli, E., Raganato, A., Pasi, G. (2024). Incorporating Cognitive Complexity of Text in Dense Retrieval for Personalized Search. In Proceedings of the 14th Italian Information Retrieval Workshop (pp.82-85). CEUR-WS. Dettaglio