{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T11:18:55Z","timestamp":1773141535507,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":18,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,16]]},"DOI":"10.1145\/3708319.3733662","type":"proceedings-article","created":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T15:17:00Z","timestamp":1749741420000},"page":"161-168","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Towards a Structured Multimodal Speech-Image Coordination"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-7123-2921","authenticated-orcid":false,"given":"Massimo","family":"Donini","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of Turin, Turin, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3448-2377","authenticated-orcid":false,"given":"Michael","family":"Oliverio","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Turin, Turin, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2161-2263","authenticated-orcid":false,"given":"Pier Felice","family":"Balestrucci","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Turin, Turin, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2292-6480","authenticated-orcid":false,"given":"Luca","family":"Anselma","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Turin, Turin, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0049-6213","authenticated-orcid":false,"given":"Cristina","family":"Gena","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Turin, Turin, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3072-0108","authenticated-orcid":false,"given":"Alessandro","family":"Mazzei","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Turin, Turin, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1975-6769","authenticated-orcid":false,"given":"Matteo","family":"Nazzario","sequence":"additional","affiliation":[{"name":"Intesa SanPaolo Innovation Center, Turin, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9748-648X","authenticated-orcid":false,"given":"Irene","family":"Borgini","sequence":"additional","affiliation":[{"name":"Intesa SanPaolo Innovation Center, Turin, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,6,12]]},"reference":[{"key":"e_1_3_3_3_2_2","doi-asserted-by":"publisher","unstructured":"Obied Alaqlobi Ahmed Alduais Fawaz Qasem and Muhammad Alasmari. 2025. A SWOT analysis of generative AI in applied linguistics: Leveraging strengths addressing weaknesses seizing opportunities and mitigating threats. F1000Research 13 1040 (2025) 1040. 10.12688\/f1000research.155378.2","DOI":"10.12688\/f1000research.155378.2"},{"key":"e_1_3_3_3_3_2","doi-asserted-by":"publisher","unstructured":"Pier\u00a0Felice Balestrucci Elisa Di\u00a0Nuovo Manuela Sanguinetti Luca Anselma Cristian Bernareggi and Alessandro Mazzei. 2024. An Educational Dialogue System for Visually Impaired People. IEEE Access 12 (2024) 49800\u201349812. 10.1109\/ACCESS.2024.3392509","DOI":"10.1109\/ACCESS.2024.3392509"},{"key":"e_1_3_3_3_4_2","doi-asserted-by":"crossref","unstructured":"David Cihak Paul\u00a0A Alberto Teresa Taber-Doughty and Robert\u00a0I Gama. 2006. A comparison of static picture prompting and video prompting simulation strategies using group instructional procedures. Focus on Autism and Other Developmental Disabilities 21 2 (2006) 89\u201399.","DOI":"10.1177\/10883576060210020601"},{"key":"e_1_3_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3610978.3640686"},{"key":"e_1_3_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3631700.3664889"},{"key":"e_1_3_3_3_7_2","doi-asserted-by":"crossref","unstructured":"Mohammadreza Farrokhnia Seyyed\u00a0Kazem Banihashem Omid Noroozi and Arjen Wals. 2024. A SWOT analysis of ChatGPT: Implications for educational practice and research. Innovations in education and teaching international 61 3 (2024) 460\u2013474.","DOI":"10.1080\/14703297.2023.2195846"},{"key":"e_1_3_3_3_8_2","doi-asserted-by":"publisher","unstructured":"Cristina Gena Federica Cena Fabiana Vernero and Pierluigi Grillo. 2013. The evaluation of a social adaptive website for cultural events. User Model. User Adapt. Interact. 23 2-3 (2013) 89\u2013137. 10.1007\/S11257-012-9129-9","DOI":"10.1007\/S11257-012-9129-9"},{"key":"e_1_3_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3450614.3463422"},{"key":"e_1_3_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/EAIS48028.2020.9122778"},{"key":"e_1_3_3_3_11_2","doi-asserted-by":"publisher","unstructured":"Kathleen McCoy and Emily Hermansen. 2007. Video modeling for individuals with autism: A review of model types and effects. Education and Treatment of Children 30 4 (2007) 123\u2013140. 10.1353\/etc.2007.0029","DOI":"10.1353\/etc.2007.0029"},{"key":"e_1_3_3_3_12_2","volume-title":"Conversational AI: Dialogue Systems, Conversational Agents, and Chatbots","author":"McTear Michael","year":"2022","unstructured":"Michael McTear. 2022. Conversational AI: Dialogue Systems, Conversational Agents, and Chatbots. Springer Nature, Cham, Switzerland."},{"key":"e_1_3_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-32967-3"},{"key":"e_1_3_3_3_14_2","first-page":"1","volume-title":"Proceedings of the Second International Workshop on Artificial Intelligent Systems in Education (AIxEDU 2024) co-located with the 23rd International Conference of the Italian Association for Artificial Intelligence (AIxIA 2024)","volume":"3879","author":"Oliverio Michael","year":"2024","unstructured":"Michael Oliverio, Margherita Piroi, Daniele\u00a0De Giorgi, Pier\u00a0Felice Balestrucci, Carola Manolino, Alessandro Mazzei, Luca Anselma, Cristian Bernareggi, Marina Serio, Cristina Sabena, Tiziana Armano, Sandro Coriasco, and Anna Capietto. 2024. NoVAGraphS: Towards an Accessible Educational-Oriented Dialogue System. In Proceedings of the Second International Workshop on Artificial Intelligent Systems in Education (AIxEDU 2024) co-located with the 23rd International Conference of the Italian Association for Artificial Intelligence (AIxIA 2024), Vol.\u00a03879. CEUR-WS.org, Aachen, Germany, 1\u20139. https:\/\/ceur-ws.org\/Vol-3879\/AIxEDU2024_paper_34.pdf"},{"key":"e_1_3_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/EDUCON54358.2023.10125121"},{"key":"e_1_3_3_3_16_2","first-page":"15","volume-title":"Proceedings of the Workshop on Advanced Visual Interfaces: Smart Interactions (AVI*CH)","author":"Sorgente Antonio","year":"2016","unstructured":"Antonio Sorgente, Paolo Vanacore, Antonio Origlia, Enrico Leone, Francesco Cutugno, and Francesco Mele. 2016. Multimedia Responses in Natural Language Dialogues. In Proceedings of the Workshop on Advanced Visual Interfaces: Smart Interactions (AVI*CH). CEUR-WS.org, Napoli, Italy, 15\u201318. https:\/\/www.researchgate.net\/publication\/311911354_Multimedia_Responses_in_Natural_Language_Dialogues"},{"key":"e_1_3_3_3_17_2","unstructured":"Qingfeng Sun Yujing Wang Can Xu Kai Zheng Yaming Yang Huang Hu Fei Xu Jessica Zhang Xiubo Geng and Daxin Jiang. 2021. Multimodal Dialogue Response Generation. arXiv preprint 2110 08515 (2021) 1\u201310. https:\/\/arxiv.org\/abs\/2110.08515 arXiv:https:\/\/arXiv.org\/abs\/2110.08515."},{"key":"e_1_3_3_3_18_2","doi-asserted-by":"crossref","unstructured":"Connie Wong Samuel\u00a0L Odom Kara\u00a0A Hume Ann\u00a0W Cox Angel Fettig Suzanne Kucharczyk Matthew\u00a0E Brock Joshua\u00a0B Plavnick Veronica\u00a0P Fleury and Tia\u00a0R Schultz. 2015. Evidence-based practices for children youth and young adults with autism spectrum disorder: A comprehensive review. Journal of autism and developmental disorders 45 (2015) 1951\u20131966.","DOI":"10.1007\/s10803-014-2351-z"},{"key":"e_1_3_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713110"}],"event":{"name":"UMAP '25: 33rd ACM Conference on User Modeling, Adaptation and Personalization","location":"New York City USA","acronym":"UMAP '25","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Adjunct Proceedings of the 33rd ACM Conference on User Modeling, Adaptation and Personalization"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3708319.3733662","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,28]],"date-time":"2025-06-28T11:14:59Z","timestamp":1751109299000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3708319.3733662"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,12]]},"references-count":18,"alternative-id":["10.1145\/3708319.3733662","10.1145\/3708319"],"URL":"https:\/\/doi.org\/10.1145\/3708319.3733662","relation":{},"subject":[],"published":{"date-parts":[[2025,6,12]]},"assertion":[{"value":"2025-06-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}