{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T03:26:07Z","timestamp":1743045967960,"version":"3.40.3"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031806063"},{"type":"electronic","value":"9783031806070"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-80607-0_6","type":"book-chapter","created":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T16:35:06Z","timestamp":1735662906000},"page":"64-78","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MM-IGLU-IT: Multi-modal Interactive Grounded Language Understanding in\u00a0Italian"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0193-2131","authenticated-orcid":false,"given":"Federico","family":"Borazio","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8204-5023","authenticated-orcid":false,"given":"Claudiu Daniel","family":"Hromei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0318-7441","authenticated-orcid":false,"given":"Elisa","family":"Passone","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9111-1950","authenticated-orcid":false,"given":"Danilo","family":"Croce","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5140-0694","authenticated-orcid":false,"given":"Roberto","family":"Basili","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,1,1]]},"reference":[{"key":"6_CR1","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. arxiv preprint arXiv:2204.14198 (2022)"},{"key":"6_CR2","doi-asserted-by":"publisher","unstructured":"Aliannejadi, M., Kiseleva, J., Chuklin, A., Dalton, J., Burtsev, M.: Building and evaluating open-domain dialogue corpora with clarifying questions. In: Moens, M.F., Huang, X., Specia, L., Yih, S.W.t. (eds.) Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 4473\u20134484. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic (2021). https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.367","DOI":"10.18653\/v1\/2021.emnlp-main.367"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Aliannejadi, M., Zamani, H., Crestani, F., Croft, W.B.: Asking clarifying questions in open-domain information-seeking conversations. arXiv preprint arXiv:1907.06554 (2019)","DOI":"10.1145\/3331184.3331265"},{"key":"6_CR4","unstructured":"Brown, T.B., et al.: Language models are few-shot learners. arXiv preprint arXiv:2005.14165 (2020)"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Croce, D., Passaro, L.C., Lenci, A., Basili, R.: GQA-it: Italian question answering on image scene graphs. In: Fersini, E., Passarotti, M., Patti, V. (eds.) Proceedings of the Eighth Italian Conference on Computational Linguistics, CLiC-it 2021, Milan, Italy, January 26-28, 2022. CEUR Workshop Proceedings, vol.\u00a03033. CEUR-WS.org (2021). http:\/\/ceur-ws.org\/Vol-3033\/paper42.pdf","DOI":"10.4000\/books.aaccademia.10535"},{"key":"6_CR6","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Burstein, J., Doran, C., Solorio, T. (eds.) Proceedings of the NAACL 2019, pp. 4171\u20134186 (2019)"},{"key":"6_CR7","unstructured":"He, P., Liu, X., Gao, J., Chen, W.: DeBERTa: decoding-enhanced BERT with disentangled attention. In: 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021 (2021)"},{"key":"6_CR8","unstructured":"Hermann, K.M., et al.: Teaching machines to read and comprehend. In: Cortes, C., Lawrence, N., Lee, D., Sugiyama, M., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol.\u00a028. Curran Associates, Inc. (2015)"},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Hong, W., et al.: CogAgent: a visual language model for GUI agents. arXiv preprint arXiv:2312.08914 (2023)","DOI":"10.1109\/CVPR52733.2024.01354"},{"key":"6_CR10","unstructured":"Hromei, C.D., Croce, D., Basile, V., Basili, R.: ExtremITA at EVALITA 2023: multi-task sustainable scaling to large language models at its extreme. In: Proceedings of the Eighth Evaluation Campaign of Natural Language Processing and Speech Tools for Italian. Final Workshop (EVALITA 2023). CEUR.org, Parma, Italy (2023)"},{"key":"6_CR11","unstructured":"Hromei, C.D., Margiotta, D., Croce, D., Basili, R.: MM-IGLU: multi-modal interactive grounded language understanding. In: Calzolari, N., Kan, M.Y., Hoste, V., Lenci, A., Sakti, S., Xue, N. (eds.) Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024, pp. 11440\u201311451. ELRA and ICCL, Torino, Italia (2024). https:\/\/aclanthology.org\/2024.lrec-main.1000"},{"key":"6_CR12","unstructured":"Kiseleva, J., et\u00a0al.: Interactive grounded language understanding in a collaborative environment: IGLU 2021. In: NeurIPS 2021 Competitions and Demonstrations Track, pp. 146\u2013161. PMLR (2022)"},{"key":"6_CR13","unstructured":"Kiseleva, J., et al.: IGLU 2022: Interactive grounded language understanding in a collaborative environment at NeurIPS 2022 (2022)"},{"key":"6_CR14","unstructured":"Koh, J.Y., Salakhutdinov, R., Fried, D.: Grounding language models to images for multimodal inputs and outputs. In: Proceedings of the 40th International Conference on Machine Learning. ICML\u201923, JMLR.org (2023)"},{"key":"6_CR15","doi-asserted-by":"publisher","unstructured":"Kojima, N., Suhr, A., Artzi, Y.: Continual learning for grounded instruction generation by observing human following behavior. Trans. Assoc. Comput. Linguistics 9 (2021).https:\/\/doi.org\/10.1162\/tacl_a_00428","DOI":"10.1162\/tacl_a_00428"},{"key":"6_CR16","unstructured":"Kriangchaivech, K., Wangperawong, A.: Question generation by transformers. arXiv preprint arXiv:1909.05017 (2019)"},{"key":"6_CR17","unstructured":"Lauren\u00e7on, H., et al.: Obelics: an open web-scale filtered dataset of interleaved image-text documents. arXiv preprint arXiv:2306.16527 (2023)"},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Lewis, M., et al.: BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461 (2019)","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"6_CR19","unstructured":"Liu, D., Lin, C.: Sherlock: a semi-automatic quiz generation system using linked data. In: International Semantic Web Conference (Posters & Demos), pp. 9-12. Citeseer (2014)"},{"key":"6_CR20","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Oh, A., Naumann, T., Globerson, A., Saenko, K., Hardt, M., Levine, S. (eds.) Advances in Neural Information Processing Systems, vol.\u00a036, pp. 34892\u201334916. Curran Associates, Inc. (2023)"},{"key":"6_CR21","unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"6_CR22","unstructured":"Lopez, L.E., Cruz, D.K., Cruz, J.C.B., Cheng, C.: Transformer-based end-to-end question generation. arXiv preprint arXiv:2005.01107 (2020)"},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"Mirowski, P., Mathewson, K.W., Pittman, J., Evans, R.: Co-writing screenplays and theatre scripts with language models: an evaluation by industry professionals. arXiv preprint arXiv:2209.14958 (2022)","DOI":"10.1145\/3544548.3581225"},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Mitkov, R., Ha, L.A.: Computer-aided generation of multiple-choice tests. In: Proceedings of the HLT-NAACL 03 Workshop on Building Educational Applications Using Natural Language Processing, pp. 17\u201322 (2003). https:\/\/aclanthology.org\/W03-0203","DOI":"10.3115\/1118894.1118897"},{"key":"6_CR25","doi-asserted-by":"publisher","unstructured":"Narayan-Chen, A., et al.: Towards problem solving agents that communicate and learn. In: Proceedings of the First Workshop on Language Grounding for Robotics. Association for Computational Linguistics, Vancouver, Canada (2017). https:\/\/doi.org\/10.18653\/v1\/W17-2812","DOI":"10.18653\/v1\/W17-2812"},{"key":"6_CR26","unstructured":"OpenAI: GPT-4 technical report (2023)"},{"key":"6_CR27","doi-asserted-by":"publisher","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: Isabelle, P., Charniak, E., Lin, D. (eds.) Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318. Association for Computational Linguistics, Philadelphia, Pennsylvania, USA (2002). https:\/\/doi.org\/10.3115\/1073083.1073135","DOI":"10.3115\/1073083.1073135"},{"key":"6_CR28","doi-asserted-by":"crossref","unstructured":"Pustejovsky, J., Krishnaswamy, N.: Multimodal semantics for affordances and actions. In: Kurosu, M. (ed.) Human-Computer Interaction: Theoretical Approaches and Design Methods, pp. 137\u2013160. Springer, Cham (2022)","DOI":"10.1007\/978-3-031-05311-5_9"},{"key":"6_CR29","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. arXiv preprint arXiv:2103.00020 (2021)"},{"key":"6_CR30","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I., et\u00a0al.: Improving language understanding by generative pre-training (2018)"},{"key":"6_CR31","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21, 140:1\u2013140:67 (2020). http:\/\/jmlr.org\/papers\/v21\/20-074.html"},{"key":"6_CR32","doi-asserted-by":"publisher","unstructured":"Rajpurkar, P., Zhang, J., Lopyrev, K., Liang, P.: SQuAD: 100,000+ questions for machine comprehension of text. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 2383\u20132392. Association for Computational Linguistics, Austin, Texas (2016).https:\/\/doi.org\/10.18653\/v1\/D16-1264","DOI":"10.18653\/v1\/D16-1264"},{"key":"6_CR33","unstructured":"Rey, G.A. et al.: Semi-automatic generation of quizzes and learning artifacts from linked data. In: Conference: Proceedings of the 2nd International Workshop on Learning and Education with the Web of Data (LiLe2012), co-located with the World Wide Web Conference (WWW2012) (2012)"},{"key":"6_CR34","unstructured":"Rus, V., Wyse, B., Piwek, P., Lintean, M., Stoyanchev, S., Moldovan, C.: The first question generation shared task evaluation challenge. In: Kelleher, J., Namee, B.M., Sluis, I.v.d. (eds.) Proceedings of the 6th International Natural Language Generation Conference. Association for Computational Linguistics (2010). https:\/\/aclanthology.org\/W10-4234"},{"key":"6_CR35","doi-asserted-by":"publisher","unstructured":"Su, D., et al.: Generalizing question answering system with pre-trained language model fine-tuning. In: Proceedings of the 2nd Workshop on Machine Reading for Question Answering. Association for Computational Linguistics, Hong Kong, China (2019). https:\/\/doi.org\/10.18653\/v1\/D19-5827","DOI":"10.18653\/v1\/D19-5827"},{"key":"6_CR36","unstructured":"Touvron, H., et al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"6_CR37","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol.\u00a030. Curran Associates, Inc. (2017)"},{"key":"6_CR38","unstructured":"Winograd, T.: Procedures as a representation for data in a computer program for understanding natural language, Technical report, Massachusetts Inst of Tech Cambridge Project Mac (1971)"},{"key":"6_CR39","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: MiniGPT-4: enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)"}],"container-title":["Lecture Notes in Computer Science","AIxIA 2024 \u2013 Advances in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-80607-0_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T17:03:41Z","timestamp":1735664621000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-80607-0_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031806063","9783031806070"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-80607-0_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"1 January 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AIxIA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference of the Italian Association for Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bolzano","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aiia2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}