List of Publications

• (See also my Google Scholar page)

• Bavaresco, A., Bernardi, R., Bertolazzi, L., Elliott, D., Fernández, R., Gatt, A., Ghaleb, E., Giulianelli, M., Hanna, M., Koller, A., Martins, A. F. T., Mondorf, P., Neplenbroek, V., Pezzelle, S., Plank, B., Schlangen, D., Suglia, A., Surikuchi, A. K., Takmaz, E., Testoni, A. (authors arranged alphabetically). LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks . 2024. [Preprint PDF]
• Mazzaccara, D., Testoni, A., Bernardi, R., Learning to Ask Informative Questions: Enhancing LLMs with Preference Optimization and Expected Information Gain. 2024. [Preprint PDF]
• Testoni, A., Sprott, J., Pezzelle, S., Naming, Describing, and Quantifying Visual Objects in Humans and LLMs. Proceedings of the 62nd Conference of the Association for Computational Linguistics - ACL 2024 [PDF]
• Bavaresco, A., Testoni, A., Fernández, R., Don't Buy it! Reassessing the Ad Understanding Abilities of Contrastive Multimodal Models. Proceedings of the 62nd Conference of the Association for Computational Linguistics - ACL 2024 [PDF]
• Testoni, A., Fernández, R., Asking the Right Question at the Right Time: Human and Model Uncertainty Guidance to Ask Clarification Questions. Proceedings of The 18th Conference of the European Chapter of the Association for Computational Linguistics - EACL 2024 [PDF]
• Testoni, A., Bernardi, R., Ruggeri, A., The Efficiency of Question-Asking Strategies in a Real-World Visual Search Task. Cognitive Science, 47: e13396, 2023. [PDF]
• Testoni, A., Asking Strategic and Informative Questions in Visual Dialogue Games: Strengths and Weaknesses of Neural Generative Models. Doctoral Thesis, 2023. [PDF]
• Lucassen, A. J., Testoni, A., Bernardi, R., Probability Distributions as a Litmus Test to Inspect NNs Grounding Skills . Proceedings of the Sixth Workshop on Natural Language for Artificial Intelligence (NL4AI 2022) co-located with 21th International Conference of the Italian Association for Artificial Intelligence (AI* IA 2022). [PDF]
• Hanna, M., Pedeni, F., Suglia, A., Testoni, A., Bernardi, R., ACT-Thor: A Controlled Benchmark for Embodied Action Understanding in Simulated Environments. Proceedings of the 29th International Conference on Computational Linguistics, COLING 2022. [PDF]
• Greco, C., Testoni, A., Bernardi, R., Frank, S., A Small but Informed and Diverse Model: The Case of the Multimodal GuessWhat!? Guessing Game. Proceedings of the 2022 CLASP Conference on (Dis)embodiment. [PDF]
• Testoni, A., Bernardi, R., Garbage In, Flowers Out: Noisy Training Data Help Generative Models at Test Time. Italian Journal of Computational Linguistics (IJCOL), 2022. [PDF]
• Chaudhary, A. K., Lucassen, A. J.,Tsani, I., Testoni, A., Are Current Decoding Strategies Capable of Facing the Challenges of Visual Dialogue?. Proceedings of the 15th International Natural Language Generation Conference, INLG 2022. [PDF]
• Testoni, A.*, Greco C.*, Bernardi, R., Artificial Intelligence Models Do Not Ground Negation, Humans Do. GuessWhat?! Dialogues as a Case Study. Frontiers in Big Data. [PDF]

(* equal contribution)

• Testoni, A., Bernardi, R., Looking for Confirmations: An Effective and Human-Like Visual Dialogue Strategy. Proceedings of The 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021.[PDF]
• Testoni, A., Bernardi, R., "I’ve Seen Things You People Wouldn’t Believe": Hallucinating Entities in GuessWhat?! Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: Student Research Workshop, ACL-IJCNLP 2021.[PDF]
• Tianai, D., Testoni, A., Benotti, L., Bernardi, R., Visually Grounded Follow-up Questions: a Dataset of Spatial Questions Which Require Dialogue History. Proceedings of the Second International Combined Workshop on Spatial Language Understanding and Grounded Communication for Robotics (SpLU-RoboNLP 2021), hold in conjunction with ACL-IJCNLP 2021.[PDF]
• Greco C.*, Testoni A.*, Bernardi R., Grounding Dialogue History: Strengths and Weaknesses of Pre-trained Transformers. AIxIA 2020 – Advances in Artificial Intelligence. AIxIA 2020. Lecture Notes in Computer Science, vol 12414. Springer. [PDF]

(* equal contribution)

• Greco C.*, Testoni A.*, Bernardi R., “Yes” and “No”: Visually Grounded Polar Answers. Visually Grounded Interaction and Language Workshop 2021 (ViGIL), co-located with NAACL-HLT 2021. [PDF]

(* equal contribution)

• Testoni, A., Bernardi, R., The Interplay of Task Success and Dialogue Quality: An in-depth Evaluation in Task-Oriented Visual Dialogues. Proceedings of The 16th Conference of the European Chapter of the Association for Computational Linguistics - EACL 2021.[PDF]
• Testoni, A., Bernardi, R., Overprotective Training Environments Fall Short at Testing Time: Let Models Contribute to Their Own Training. Proceedings of the Seventh Italian Conference on Computational Linguistics CLiC-it, 2020.[PDF]

(Special Mention)

• Greco C.*, Testoni A.*, Bernardi R., Which turn do neural models exploit the most to solve GuessWhat? Diving into the dialogue history encoding in Transformers and LSTMs. Proceedings of the 4th Workshop on Natural Language for Artificial Intelligence (NL4AI 2020) co-located with the 19th International Conference of the Italian Association for Artificial Intelligence (AI*IA 2020), 2020.[PDF]

(* equal contribution)

• Testoni, A., Greco, C., Bianchi, T., Mazuecos, M., Marcante, A., Benotti, L., & Bernardi, R., They are not all alike: answering different spatial questions requires different grounding strategies. Proceedings of the Third International Workshop on Spatial Language Understanding (SpLU), co-located with EMNLP, 2020.[PDF]
• Mazuecos, M., Testoni, A., Bernardi, R., Benotti L., On the role of effective and referring questions in GuessWhat?! Proceedings of the First Workshop on Advances in Language and Vision Research, ALVR co-located with ACL, 2020.[PDF]
• Shekhar, R., Testoni, A., Fernández, R., & Bernardi, R., Jointly learning to see, ask, decide when to stop, and then GuessWhat. Proceedings of the Sixth Italian Conference on Computational Linguistics CLiC-it 2019.[PDF]
• Testoni, A., Shekhar, R., Fernández, R., & Bernardi, R., The Devil is in the Details: A Magnifying Glass for the GuessWhich Visual Dialogue Game. Proceedings of the 23rd Workshop on the Semantics and Pragmatics of Dialogue - SemDial, 2019.[PDF]
• Testoni, A., Pezzelle, S., & Bernardi, R. Quantifiers in a Multimodal World: Hallucinating Vision with Language and Sound. In Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics (pp. 105-116), NAACL HLT, 2019. [PDF]
• Vu, H., Greco, C., Erofeeva, A., Jafaritazehjan, S., Linders, G., Tanti, M., Testoni, A., Bernardi, R., & Gatt, A. Grounded Textual Entailment. In Proceedings of the 27th International Conference on Computational Linguistics (pp. 2354-2368), 2018. [PDF]
• Testoni, A., & Di Felice, M. A software architecture for generic human activity recognition from smartphone sensor data. In 2017 IEEE International Workshop on Measurement and Networking (M&N) (pp. 1-6). IEEE, 2017. [PDF]